[
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5679608237702286,
    "sentence_nr": 0
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.746881923400435,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4438455475739657,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6320800718582147,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5894973558751632,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7562097956860054,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3846086976522069,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5835344719191324,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4804215535486392,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6694735319785804,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2511517944602615,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4484633445384819,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5820808184424484,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.73788733854976,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5749603738163459,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7240488251574404,
    "sentence_nr": 0
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5617561349997696,
    "sentence_nr": 0
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7132694856647042,
    "sentence_nr": 0
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2963216580569375,
    "sentence_nr": 0
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5101500486835966,
    "sentence_nr": 0
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15317719477157257,
    "sentence_nr": 0
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.38800976493585004,
    "sentence_nr": 0
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6001453932849357,
    "sentence_nr": 0
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.762029391170019,
    "sentence_nr": 0
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30676942927198475,
    "sentence_nr": 0
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4968492831219663,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32063971770635635,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5206258401513325,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.39086127104761287,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6239956806265569,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3020679767949182,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5246291817407542,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.29261990846502584,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5207965578474395,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23343658187420896,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5188968707275573,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2920008662633279,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.47119207959541226,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2596939072050362,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4394574387008692,
    "sentence_nr": 0
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4273817965049865,
    "sentence_nr": 0
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6016204186733703,
    "sentence_nr": 0
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 0
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 0
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 0
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2777551012631926,
    "sentence_nr": 0
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49423240120783246,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7964573357809173,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8458636471716781,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.34633672321253084,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5378805625051344,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3582301850807646,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5380305837807603,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.300740577257699,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5272774705181614,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3099603853356145,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5209233176748354,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.35580399268816465,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5392592206305507,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.39317381456022266,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6026058740561834,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.48930936408255293,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.699085629239476,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3963410285961713,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.613166190285915,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.44294247711132617,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5915660675216782,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3756985486608933,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5991443770283833,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5009456904181451,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6893719644090858,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18273944860385094,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.44261865187418153,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2153742037697241,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4581737688885401,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3372953649368346,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5482505380106469,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.28528905353056333,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4885812318466243,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2935204022158406,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4867597973247361,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2929684584911775,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5038324436049059,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4034224234291925,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5736798834726872,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1077205146963877,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.428338145564396,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.22327767951697297,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4063556880747369,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2572733200413211,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4520014138562526,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.40311197004738203,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5788525108956781,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.45313578977486535,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6160993561903745,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2651736858432996,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4491383344282561,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.34545319957597864,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5727052860304503,
    "sentence_nr": 0
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15815751066481462,
    "sentence_nr": 1
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5152611872266766,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12903696060775005,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.456225988032654,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.024459391267874976,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12351824822447692,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.46822754470803873,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3465147345201782,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.08516700886866406,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4091252890943268,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19194937906573872,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5477665664300843,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4370196290761142,
    "sentence_nr": 1
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20669086265781264,
    "sentence_nr": 1
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5076721272198604,
    "sentence_nr": 1
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17630490037560695,
    "sentence_nr": 1
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.48116430160978857,
    "sentence_nr": 1
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4122750002638689,
    "sentence_nr": 1
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15412719160788987,
    "sentence_nr": 1
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5010353699512481,
    "sentence_nr": 1
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12369892692249995,
    "sentence_nr": 1
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.44549610902403686,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12560672881768975,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4969560260291519,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17077058518804336,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5022008374701596,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10784756064735967,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4427230465401631,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.06735571462439276,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.38102852892512806,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.42723260976616784,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1694466724647263,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4902502031746037,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3532931581623198,
    "sentence_nr": 1
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.175396614619324,
    "sentence_nr": 1
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49736499605529066,
    "sentence_nr": 1
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15154395847232716,
    "sentence_nr": 1
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.46053919348995803,
    "sentence_nr": 1
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4041678259311437,
    "sentence_nr": 1
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1290514243115152,
    "sentence_nr": 1
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4766581477336301,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.08273178236238297,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36399666460809255,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12601482779921785,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43595665254608706,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.40959087443621306,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6348509381122925,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.08214106568089705,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3969463877642616,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0744904632040495,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4111163205685468,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12894104034845807,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4486368934849452,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10070927557742705,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43718220262892105,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0772718393063023,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4203683137304257,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0756907193511249,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4138725093679467,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21748353646757182,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4462746462826943,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4179644538349004,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10505106462290037,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4474870048911137,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0009218289085545725,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15653859793617866,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43177798053127925,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0891537192318598,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3970634926176537,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0950136506275681,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4372017487229785,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1259356760989446,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.44568274520971096,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16322494183480127,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4815584993817062,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0904087252785689,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41830513174690515,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21351902664706998,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5130443042033361,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.16269986423611488,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.06939838145153245,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3371547585108182,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1691386174483793,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4920789340026317,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14944432524273302,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4972796478830659,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09793316925795417,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4297577431879659,
    "sentence_nr": 1
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.38870674200492367,
    "sentence_nr": 2
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6484380084879691,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4923751299732868,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6853756490381199,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3996712647649035,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6353525755760105,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5115346945020283,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7037574715738644,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.017834618169115152,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.05927156798818119,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23904922011090457,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3399292774084129,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6152980280400979,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8311281590297233,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.005449161724399305,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.026158029267484995,
    "sentence_nr": 2
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.24508104771894088,
    "sentence_nr": 2
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5725552336126134,
    "sentence_nr": 2
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 2
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 2
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20801258614305904,
    "sentence_nr": 2
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.26703508536995574,
    "sentence_nr": 2
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.35315040956049437,
    "sentence_nr": 2
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.625895188503691,
    "sentence_nr": 2
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11133996756497437,
    "sentence_nr": 2
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4410280353998367,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17743299460161885,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43071271897416463,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16052654068024738,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41580120868053494,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.05963579607071745,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.31139762378406344,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.006734847287559362,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.03408121951468736,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09880177230676102,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3297638349619511,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2377604053257556,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5662768009060447,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.22573408807826306,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5444672928195973,
    "sentence_nr": 2
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10742716472890976,
    "sentence_nr": 2
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.42694859148910824,
    "sentence_nr": 2
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 2
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 2
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 2
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 2
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14745870033404418,
    "sentence_nr": 2
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.475170637938921,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21665407194210906,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4344921442639243,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.37994652561206577,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6464467277069994,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09362261118571368,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3452056942265759,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18917620656425485,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4346170232980484,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.420450507904553,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6503146347305717,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.24894072982768842,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5212235893093335,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.393613605227227,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6492198447661237,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21147734744561483,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41020178654369294,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2329856851831642,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5405751250637106,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.41756686236967944,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5616829345739638,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.38189567401226293,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6154314825900052,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2126707920684064,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4659908460634765,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23240102389974368,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4973274282641141,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17979384730979156,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4177311931467539,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1702602472176709,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4366640707779677,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.933651069586263,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9586507529693243,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3816408219023713,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5784105768028126,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18398226639192106,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.37285010531146734,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.26958884543190903,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5631664732610485,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4005296397635166,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6201785376974677,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15956483578595942,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.425693420655628,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2323385180696658,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5019509292309764,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.22952177306405494,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5279520952576137,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3618488169166299,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5708179622131996,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1712766252338756,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5225554962608486,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2709079038456153,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.447458019441992,
    "sentence_nr": 2
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.38249626297768063,
    "sentence_nr": 3
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.40976234193505356,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5806197937310393,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7346706700987636,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5793367580502561,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6502428441722727,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4855332614117322,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5299556742893647,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19940445989088915,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43164821827950184,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2423441824135159,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4429509373913047,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6242817472465665,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7056438934239434,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6064630666233242,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6752055521830945,
    "sentence_nr": 3
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5357110024227318,
    "sentence_nr": 3
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6365941772753647,
    "sentence_nr": 3
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 3
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 3
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14790264259417688,
    "sentence_nr": 3
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.27159767590045303,
    "sentence_nr": 3
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4751132438608344,
    "sentence_nr": 3
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6849386986272349,
    "sentence_nr": 3
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.08635800047213174,
    "sentence_nr": 3
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.218109371254876,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23386786214190372,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3682311523733465,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11739521786077453,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22090491782919655,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1892240568795935,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.280413108453108,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11547518641061649,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.25945846414490087,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20233074088759792,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3746629492952356,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.40214612768560637,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.45128424593135114,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.37284875432797243,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.44888401040760956,
    "sentence_nr": 3
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0925329498915617,
    "sentence_nr": 3
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2110486160692096,
    "sentence_nr": 3
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 3
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 3
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 3
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.12453389344594705,
    "sentence_nr": 3
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.141543757252386,
    "sentence_nr": 3
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2594145364221844,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6244631487487835,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6931369519059803,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.25383339228798274,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.45896379476820603,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17200767571780612,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3723150838362789,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1477219991186121,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28685201698226354,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3254455687469726,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4474512036484817,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23887527917609022,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4120359948636439,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.580451128369423,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.728208634600343,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3556521383601747,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.594830811413066,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21629114799587432,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3542320138389837,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.580451128369423,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.728208634600343,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.27405612859390877,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4639958592456083,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13004800471424346,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28217142159025543,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.37821486365532614,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4718665834023439,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3699382260470039,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4032851361478274,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.45167594566243024,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5169677927619225,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23386786214190372,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3780009826926042,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3925121365052661,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.47788592802001717,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1423412184218882,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2596718628394258,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3572188192648703,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.45381175288762937,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.07425055521504613,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18122341046764998,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1978585723043446,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3527599187160617,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2523019529343173,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4406369072888057,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.41072675483179805,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5635589150380774,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3883375900135818,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4643731845106876,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6242817472465665,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7123666275414222,
    "sentence_nr": 3
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8003203203844999,
    "sentence_nr": 4
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9453478043428296,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2246029757863831,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5773502691896258,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7999099314029202,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6417603075499863,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7825422900366437,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8503171627677965,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.37709297891717664,
    "sentence_nr": 4
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6881502501430368,
    "sentence_nr": 4
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8003203203844999,
    "sentence_nr": 4
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9453478043428296,
    "sentence_nr": 4
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.629039349740581,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.629039349740581,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.629039349740581,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5581982021478125,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.629039349740581,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.652013511062815,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.629039349740581,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.629039349740581,
    "sentence_nr": 4
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.629039349740581,
    "sentence_nr": 4
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.629039349740581,
    "sentence_nr": 4
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.629039349740581,
    "sentence_nr": 4
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.629039349740581,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5881561248602009,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.40435987083533204,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.39858613265631837,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4425973012069069,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.47160616105623426,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5309982646782259,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1892240568795935,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6151179643430991,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41238100267720657,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.39909989628767284,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17181529671327242,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5293474685884572,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4429196299668147,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3830425592586042,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1667955161379731,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5802683403568892,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3237722713145643,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7426638026175545,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49342175914364256,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4352628824108997,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5116862201536014,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.33471616336068044,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2865612242047131,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6433813179203622,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3598792258309727,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5125809225356253,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5539920925426138,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5226572946586268,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5073395824633415,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.29382595610734974,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1667955161379731,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5773664661124461,
    "sentence_nr": 4
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7013062757071812,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9303769449292738,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2381658499765768,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8492326635760689,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9063898435384111,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5309354663044072,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6756014232714684,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4529852871970908,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6941474239078328,
    "sentence_nr": 5
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8522456714074852,
    "sentence_nr": 5
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9096914044088521,
    "sentence_nr": 5
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9457416090031758,
    "sentence_nr": 5
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9892952933418456,
    "sentence_nr": 5
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.47410002229034043,
    "sentence_nr": 5
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7538467008030766,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5087473540251254,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7647955332172516,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5087473540251254,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7647955332172516,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.47410002229034043,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7538467008030766,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4234885228074744,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7410180114887145,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.47375069012411286,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7543919667018285,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5738396574789242,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.798357133373606,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5738396574789242,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.798357133373606,
    "sentence_nr": 5
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.47410002229034043,
    "sentence_nr": 5
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7538467008030766,
    "sentence_nr": 5
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.47410002229034043,
    "sentence_nr": 5
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7538467008030766,
    "sentence_nr": 5
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4234885228074744,
    "sentence_nr": 5
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7410180114887145,
    "sentence_nr": 5
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.47375069012411286,
    "sentence_nr": 5
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7543919667018285,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5091224918749461,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7829685247145245,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.40276720463657734,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6529271690805427,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30188353873287377,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6086565367747951,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6026286934891149,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8025775976044891,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4596980088392874,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.713787745993602,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3272712268138726,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6272846474183881,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2981792160679168,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5788026000794341,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7012294787544179,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8478115719875968,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21690365808279138,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5384773678665918,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.25711386542134795,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6088853751738869,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5695988432761473,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7516103467926585,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5072784644062104,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7361065921505279,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.38091370416670794,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6438225861756911,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5091224918749461,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7202697992734389,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6917901740466924,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8479928839177578,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5309354663044072,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6990707992725005,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1673872929477023,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4506667273103674,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6917901740466924,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8479928839177578,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3416581331218724,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6578570934289981,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4797543511401896,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7240781310560407,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6401876410870359,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7526484951226097,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33057129676705455,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5669225664686625,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6004981752197522,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7697646564917222,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8492326635760689,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9027320255916917,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30350690419450826,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.569133886912883,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6834516951654327,
    "sentence_nr": 5
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3263040636562357,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7511573912724299,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9453473543978153,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5971070986250356,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8874294965619517,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7511573912724299,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9453473543978153,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7511573912724299,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9453473543978153,
    "sentence_nr": 6
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7511573912724299,
    "sentence_nr": 6
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9453473543978153,
    "sentence_nr": 6
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7511573912724299,
    "sentence_nr": 6
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9453473543978153,
    "sentence_nr": 6
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7511573912724299,
    "sentence_nr": 6
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9453473543978153,
    "sentence_nr": 6
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19464521962073492,
    "sentence_nr": 6
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5838790966762375,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3142665434344143,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6466526067220029,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3751840463233443,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6279894552667558,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19268479640608693,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.551397074868541,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17470942957770763,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5403400891349619,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19464521962073492,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5763410052067085,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.37392149096896676,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6665214662145853,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19464521962073492,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5838790966762375,
    "sentence_nr": 6
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19464521962073492,
    "sentence_nr": 6
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5763410052067085,
    "sentence_nr": 6
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 6
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5460240376042262,
    "sentence_nr": 6
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.24343304284910333,
    "sentence_nr": 6
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6275577931282961,
    "sentence_nr": 6
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.28571962561926445,
    "sentence_nr": 6
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6431872581462166,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6255340042200862,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8724783049357475,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.48994561421713123,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7411155087367244,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5971070986250356,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8874294965619517,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4547900039222725,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6541971428810075,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23198210427894825,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.630711601223299,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4831233610237384,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7122562458056777,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32263864160302524,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6824395076981005,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.38305978177479755,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6061131723054572,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.24047860794644352,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.58198979036704,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7511573912724299,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9453473543978153,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42984824697674956,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7289444696770301,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4881010344921759,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7317734491561229,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5971070986250356,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8874294965619517,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3684981984538114,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5606332518476288,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4536404448264584,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8020827133708689,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4545091839935173,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7166050399790445,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3370129264673147,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7096874943799061,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1624355752882384,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4952968469712617,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4831233610237384,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7807505267551733,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5595205105615875,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8322210048001876,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3142665434344143,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6466526067220029,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3610544299180199,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49125115898082056,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4284945090100314,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7164026439677106,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8578928092681435,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9422733087334002,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.42818224355402373,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42105372680687736,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7001171094008295,
    "sentence_nr": 6
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1582866049832572,
    "sentence_nr": 7
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.34487142413575794,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15521606028436608,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.37645329404497957,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12620429887108936,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.35580703793872603,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12872220631084524,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.33602633953270183,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.042121062429802174,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.14281404499176092,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.042575418285137674,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.05173688961049459,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3045613775157565,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5275070803493389,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2734283774929853,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5252214120598302,
    "sentence_nr": 7
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10203846572325131,
    "sentence_nr": 7
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.33381153680096753,
    "sentence_nr": 7
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 7
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.014935758919429663,
    "sentence_nr": 7
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.08106107745254391,
    "sentence_nr": 7
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.044304867337633724,
    "sentence_nr": 7
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20806974344498103,
    "sentence_nr": 7
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.08860973467526746,
    "sentence_nr": 7
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3178004360288637,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15268019045355535,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41028757620299977,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.030860166165309233,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1100250143829584,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21255327712152144,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43272151570555034,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.01486609147288197,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.13893773605583024,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.06609667473412645,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.26197209338359717,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.26064517697298795,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5092206110218525,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1507980395794452,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4306039128585424,
    "sentence_nr": 7
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1438459189500836,
    "sentence_nr": 7
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30693371625402605,
    "sentence_nr": 7
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0979038733644086,
    "sentence_nr": 7
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30211704738953993,
    "sentence_nr": 7
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.009624974244068071,
    "sentence_nr": 7
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.07318255686027669,
    "sentence_nr": 7
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.043420474648595074,
    "sentence_nr": 7
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2884095690753619,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13868172938464635,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3094469764260441,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11091252683001185,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.26607634610445896,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18154954789336694,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4557483776072868,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1381751568911733,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3121557499162649,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20065115069964384,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4084885616013531,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12291219097556666,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3448002180666873,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20608572305725564,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4704943905570542,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.085416483900781,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2825804066750608,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11452508920842025,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3212742401272785,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15478222669012726,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3550584759508654,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.07875433150726119,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2638954513805452,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10734088848154077,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.33946796348247366,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17795920517030017,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41862955401967455,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19388048412249795,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.44361702376789247,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1237012344369667,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.33331866832253354,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15589802574348086,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.37894206802233305,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1948502778967486,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.35525815981538433,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1618333627385132,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3458746996740858,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17393111207515277,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.39042812195808824,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19064689695123957,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36954921822756504,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1785851272602057,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3800733399524004,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20113943179758872,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5054929215592371,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.07088281524771703,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1725752257112697,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11901413329120636,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2908877283991857,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15593857496482408,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3832822126692406,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21107720643690867,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43911506176829573,
    "sentence_nr": 7
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13410301071131794,
    "sentence_nr": 8
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3942932268034351,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30677064886592076,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5308555945242818,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1327526847508867,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.37850602486495205,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18405035438430847,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4142901090120915,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.061826017721563604,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.08852681798207009,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3583179111355935,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3857436691295343,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5750224388123065,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5920893212447781,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6925021521158101,
    "sentence_nr": 8
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.22478613858269392,
    "sentence_nr": 8
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.44348101018104913,
    "sentence_nr": 8
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 8
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 8
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 8
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.183687049781416,
    "sentence_nr": 8
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.351911486970854,
    "sentence_nr": 8
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5181825846579515,
    "sentence_nr": 8
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17328174803055044,
    "sentence_nr": 8
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3178268797869574,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.286608441075188,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4579283646292802,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.25861130592298187,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.39452644092432093,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20379250618355427,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41085414309816914,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.310679343206099,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4471183729584148,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2334787866969297,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3621517589760531,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5866873582151947,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.46269559069048716,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.46872641361415845,
    "sentence_nr": 8
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10434360980785336,
    "sentence_nr": 8
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3012789660952507,
    "sentence_nr": 8
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 8
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 8
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 8
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.13835317113453516,
    "sentence_nr": 8
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16343842313572918,
    "sentence_nr": 8
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3986641525285075,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30890092021323623,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5553909583113487,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1690979933029136,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3751861276375209,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2840563956846642,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5110250591004448,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19920413481788912,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.42537796926163113,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20401796878756984,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43317630453631556,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2044887070217883,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.38471585132587544,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2980504190448601,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5101268920225042,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9436043261706615,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9880191679951993,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18831933500600306,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4318025704181776,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21544027588567594,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5040038440508637,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.26970223719007375,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5172978597562362,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30630098078522544,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5439056051092116,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19850842371858787,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43584341835040474,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20170335119323748,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3541251997977811,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10508106635796587,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3182774828667731,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2309552734743087,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43975656978777905,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23530033724858213,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.46208607300298377,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.37284027455688556,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5528347504734102,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2887308472548599,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.38846174119508314,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15487293534817623,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.39293494862736383,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21741853044139284,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3535910166292039,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33626819961829335,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5466581859383387,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32000331642122953,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5480591855923784,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21132630077912357,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4175670766052166,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13108369255325433,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3929302741911199,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20174045447955946,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.33729298835089516,
    "sentence_nr": 8
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20972571494011877,
    "sentence_nr": 9
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.395894071208527,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.35369375385786006,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13087682931309413,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.19462952976787054,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.013538497707846785,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1570208067577934,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4113045280468524,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15082713742973322,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3965911699770542,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15471428129658016,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4580211317461481,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18928475425929295,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4916060435820526,
    "sentence_nr": 9
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21940429389247643,
    "sentence_nr": 9
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4343280866601455,
    "sentence_nr": 9
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1824401863423467,
    "sentence_nr": 9
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36709433185688595,
    "sentence_nr": 9
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3377854698776805,
    "sentence_nr": 9
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.521201229892482,
    "sentence_nr": 9
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12475846123062707,
    "sentence_nr": 9
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.27823340731817514,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10759927692349745,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21065794536310511,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.07843772989359644,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1324578891826276,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.08163977068875294,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09047502044256338,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21669141850731985,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10322985794794913,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.24491122482530842,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11809057094812304,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.27930342777387007,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21268444697113978,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3229997133764549,
    "sentence_nr": 9
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1475503033983142,
    "sentence_nr": 9
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22104108935973044,
    "sentence_nr": 9
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16434349396840395,
    "sentence_nr": 9
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28582614857210975,
    "sentence_nr": 9
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10085167559661873,
    "sentence_nr": 9
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.23831215045289575,
    "sentence_nr": 9
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17543744527808774,
    "sentence_nr": 9
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28201016956553354,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12274092982883021,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3385513651938691,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.31017716089889963,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21688283061839067,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41775824162589076,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12162779391619735,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3228288840559658,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18237599479708327,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3740403511567824,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12876689524369925,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3253153379449275,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.119159749312327,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21297942664093145,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2036348471340078,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3472831655579266,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.24362353508932386,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28135849152758385,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14482189302397735,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2913876815877049,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.16306957103469613,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9199349282509897,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28112283847231073,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1308613527030366,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3063146286877558,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12787395553510186,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21931515993565381,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1441966459257424,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.14957316612525498,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.27675048474641756,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3780460244391623,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12503614625842938,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20624064341134082,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3368893372278425,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2961559727627133,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12846497020051437,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2670865602673704,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.28252374116432993,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3549531183419122,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.26128489301072644,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2126837065505244,
    "sentence_nr": 9
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.07149097424598219,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7774075575820374,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8943538262827356,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18639667871924825,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4540232715517938,
    "sentence_nr": 10
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8431643718744966,
    "sentence_nr": 10
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9341410275694613,
    "sentence_nr": 10
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.47095916883357913,
    "sentence_nr": 10
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.701526330557871,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.38260294162784475,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6692418584049541,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4093629115744712,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6243156092220487,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.36703839483583006,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6725357332891145,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4322450379367835,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.697398762810304,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.41122010762096617,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6697492221087861,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.41126318495820946,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7254294465493162,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4682601513034942,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.691130012325589,
    "sentence_nr": 10
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.35334199245807973,
    "sentence_nr": 10
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6858610070406853,
    "sentence_nr": 10
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 10
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33061666631099795,
    "sentence_nr": 10
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5343307680770133,
    "sentence_nr": 10
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.38981415389445495,
    "sentence_nr": 10
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.665622189515994,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3223937524276847,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6719135382778884,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4466645979681496,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.714247354760266,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6233091888805312,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7757111039890131,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33414322499224436,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7159580680193959,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6620694102966999,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7893416551805176,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.26540383860058264,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.51610805930355,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.49335830881778164,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7240615166053675,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4024279293206815,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6798070651801875,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6153147385756811,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8160952378322835,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6838493012537611,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8178509424142287,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5169198985488462,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7879691803533485,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5223010192696725,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7442134884509299,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3885151883045163,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6763151870864087,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5985488590218004,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8248561222494313,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.37163791993879014,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6792432753943116,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5152630372775983,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7696821316655393,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.43521980294891405,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7204319998551938,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.46417187236805535,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6653227698984816,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.519124054532681,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7733428788002137,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5083170211670072,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.755952798269267,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3161432307247198,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5990810117425377,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.40980949787910764,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7145653936496129,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5770135999436572,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7697316849447288,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7030214416074754,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8357829168322639,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.49199339399396913,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.713934780293142,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5002824356846001,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7029341279811726,
    "sentence_nr": 10
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.029124970213905314,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1779610499753793,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.05989397907532586,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.13539167567510446,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.03073685498855941,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.08933758530290428,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21051269871304829,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18854722085547196,
    "sentence_nr": 11
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1387123733773652,
    "sentence_nr": 11
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.05499461839884487,
    "sentence_nr": 11
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.19978068293555115,
    "sentence_nr": 11
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1388011701223677,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1460389336009171,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.038796252164058714,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1756002877791377,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0029868578255675027,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.015380253532528225,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.19065171436703615,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21083781655774478,
    "sentence_nr": 11
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.14590438247348272,
    "sentence_nr": 11
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.04379419293412465,
    "sentence_nr": 11
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.15119622228734425,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21315318926996712,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.16991425356152365,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22371589981083434,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20982178138488494,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20189358781069322,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20261685251676126,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.226729844497646,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18184342512086546,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2185121523322681,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.17386106914161167,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.08272059515141832,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1814025725787457,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.23945930551153607,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20815933215961574,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.09886053260067004,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.14345644530149382,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.19097844728039898,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.08246021416977749,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18868639139421345,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20665565461558383,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.17764901410543646,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.19312651305380893,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21371557282714232,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18854043679878274,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.19559831357902827,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1914895496057553,
    "sentence_nr": 11
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6666935927206881,
    "sentence_nr": 12
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7957561291403441,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.34999116613463505,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6356075517191035,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.48649824146709,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6763447333054696,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.367622917844187,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5615050712672139,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4081538556642202,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.46386216052527535,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4300174433641992,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5099800158255156,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7963205130973803,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8101688749569373,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6570128212612868,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6262090565616182,
    "sentence_nr": 12
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5866943184579982,
    "sentence_nr": 12
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6390393619950272,
    "sentence_nr": 12
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 12
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 12
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 12
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.01047222192173988,
    "sentence_nr": 12
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5683565265173782,
    "sentence_nr": 12
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7072367582469653,
    "sentence_nr": 12
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 12
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20287366424876002,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5368464080033196,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5198707241967666,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6993305416237223,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.36603776814499195,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.45532918164901276,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.13525036115537795,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3120848453730729,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3474347870952493,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7073395735740273,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6577952971578602,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6570128212612868,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6221526807313811,
    "sentence_nr": 12
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5460462259563637,
    "sentence_nr": 12
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6641829079106271,
    "sentence_nr": 12
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 12
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.04884431803904408,
    "sentence_nr": 12
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 12
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18357384275951122,
    "sentence_nr": 12
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.28073304156067924,
    "sentence_nr": 12
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.360657984953223,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.46365764298816153,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5757521453586436,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3147715014841853,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5986154863155839,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3885646234110734,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5051669760132699,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.464413403675355,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6291656356697347,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30490938758882236,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.579088460457721,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3758073513458154,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5302950018189692,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.29308025637967977,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5715200997140051,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.43285599641891276,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5551678521355665,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.25984882476296983,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6305744214119023,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.48649824146709,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7255446918266525,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.464413403675355,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6853183317800515,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.34999116613463505,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6356075517191035,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4426623526629488,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.612058732370435,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5522004843736675,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6166558670381421,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.37954187220913477,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5550325994532472,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3147715014841853,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.521228891025682,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3964513253420688,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6095420129111676,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.36033217429111203,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5550014071110869,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33403925633579773,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5753930328058733,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.44882520213790794,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5856175239899348,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42760828727369016,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6065010489098535,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33403925633579773,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5915394296427854,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3212785834179169,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6158121620368939,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1751489536280261,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.378593296276962,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3214110553053944,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49232390716994445,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.479033905070678,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5975149526416976,
    "sentence_nr": 12
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13150403915662862,
    "sentence_nr": 13
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21177549089429396,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1424915360855107,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.23985076149753726,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13309638637723345,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18696197122203645,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12256515595630638,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.23303109995893123,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1419886619859991,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.24113733359485448,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1324448705928064,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22863839042697148,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12017886776600228,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20794486026487116,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1164257728844972,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.19249901344360867,
    "sentence_nr": 13
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12325384013681445,
    "sentence_nr": 13
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1960232617116645,
    "sentence_nr": 13
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12806473847444227,
    "sentence_nr": 13
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20054688779645718,
    "sentence_nr": 13
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1345714227066951,
    "sentence_nr": 13
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21078968525268058,
    "sentence_nr": 13
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1802615495980454,
    "sentence_nr": 13
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.19630112442374525,
    "sentence_nr": 13
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8212614342207556,
    "sentence_nr": 13
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7876222308170935,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5888582552569348,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7876222308170935,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5888582552569348,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7876222308170935,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6871546336787117,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6871546336787117,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.43550490048931545,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6419345531187637,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17539593635425982,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3139104155809725,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.39225487001250453,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5189967318357492,
    "sentence_nr": 13
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12859070457371286,
    "sentence_nr": 13
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22162336097079333,
    "sentence_nr": 13
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6871546336787117,
    "sentence_nr": 13
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6258765997974801,
    "sentence_nr": 13
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6680248455809015,
    "sentence_nr": 13
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6258765997974801,
    "sentence_nr": 13
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6722124517361844,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.17023327167529265,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2521455524828544,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13150403915662862,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2229548791980166,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.15247670030930355,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1324448705928064,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.23382021475411732,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09766807787022613,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.16788063248730647,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12111615182138995,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21505717177216926,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09979796185764318,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1310501345458609,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11512937599552589,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1852451960926282,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.126642985054506,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20913543330915318,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12632059501697884,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22490978846607526,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1352612651586241,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22176710342008016,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18982400330057914,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11760179026027952,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.19531596229980544,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09968269909242322,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.14510210137368384,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1204925245474865,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12192273449574796,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18177358407861108,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.16841504132177978,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10667790151233097,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.17427579502643556,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1508875367739971,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20889434105456664,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13184959768302618,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30505662513933907,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09878901581794378,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1651800705978423,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13150403915662862,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20736628090200235,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11824658049755846,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2047497542808756,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1461072488843534,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1946917085815184,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1018151014848322,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.14524830913329922,
    "sentence_nr": 13
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2589080403198245,
    "sentence_nr": 14
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2189767496390278,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.09761931247072746,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1397102655312677,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1326689502117876,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.167569694983793,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.15848968577272604,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.24447662789322752,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20665940380705064,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18243716955007858,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.16168125580314086,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2450013599045987,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20901732384345645,
    "sentence_nr": 14
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20222677481313764,
    "sentence_nr": 14
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18492694642397273,
    "sentence_nr": 14
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18243716955007863,
    "sentence_nr": 14
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.16667457585564618,
    "sentence_nr": 14
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 14
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.08556679632324991,
    "sentence_nr": 14
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1575852366903021,
    "sentence_nr": 14
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1474874322154398,
    "sentence_nr": 14
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9202663016973823,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9263876898254182,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8621431910551439,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8363304387269249,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9419492177147062,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9202237383102091,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6656058483395763,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6306557167105028,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8657947138469048,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8367521498141209,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9419492177147062,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9202237383102091,
    "sentence_nr": 14
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6993348038140574,
    "sentence_nr": 14
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6335836519040372,
    "sentence_nr": 14
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 14
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9419492177147062,
    "sentence_nr": 14
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9202237383102091,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11064738383914807,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.12449466772796605,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12222372495044852,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.12383047729216191,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1392580908972882,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1333265070823728,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.07717159074475938,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.09413026539458375,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16807498532991816,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.16404257857373192,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21005284223037346,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1679703861465872,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0951509584925814,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.12014553061064691,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11737915185320068,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.10085050674562507,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11377195287577829,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1301681094143453,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09455636771034115,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.11463120929696417,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1544787887603271,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1384236976807813,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.11488572123868507,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1455973492295447,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.13735441291745387,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20255423961944058,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.205408273869532,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11470196605012067,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0960438892364715,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.07184436307032757,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20378989148152887,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.16337212771611656,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09669863605676213,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.10886215421099144,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18171364159867548,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.16245793974098002,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.07562263205281951,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.09819928715831736,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1430606569063152,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.128073928655324,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.09526781380423786,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18223449608285797,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.17127401148639734,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.09855718610544388,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09669863605676213,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.11679541132562438,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09643517424337235,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1226126790254367,
    "sentence_nr": 14
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3969253441303859,
    "sentence_nr": 15
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43277080710930865,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.26887073704667247,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2918476164856665,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5183146371291372,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5942793492554739,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.028864519535915668,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13535086012687783,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.29687399422087424,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.002376388269368755,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.04574695485583133,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2703094106380642,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2982249908859,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.29313061087267483,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30295384730328956,
    "sentence_nr": 15
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.284911205299835,
    "sentence_nr": 15
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.32067889250923776,
    "sentence_nr": 15
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.29353055611145706,
    "sentence_nr": 15
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3381266475327612,
    "sentence_nr": 15
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09910529437987022,
    "sentence_nr": 15
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2511990291834263,
    "sentence_nr": 15
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.295394335805579,
    "sentence_nr": 15
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.362515947701148,
    "sentence_nr": 15
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7243776840931383,
    "sentence_nr": 15
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8980107630353439,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9325718821645923,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9490053815176721,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6653044831075519,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7986980418662383,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8504591592783618,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8980107630353439,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5950322600507224,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7090542316843602,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.44768974737795825,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.45520472994232203,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6509298345623671,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7962234681835563,
    "sentence_nr": 15
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.41813929088914065,
    "sentence_nr": 15
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4779008399806691,
    "sentence_nr": 15
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7243776840931383,
    "sentence_nr": 15
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8642805496461259,
    "sentence_nr": 15
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9506885335787997,
    "sentence_nr": 15
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9606382935593174,
    "sentence_nr": 15
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8665175293126633,
    "sentence_nr": 15
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8642805496461259,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.342569723746894,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.47156710056973744,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2319934375578505,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3367678538644817,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2261681529206079,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2647144854968396,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.35554722872430145,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.38873710544604445,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3720000272862786,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.44695658930348453,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4118588818865406,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.48573453292579605,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2998354233286452,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41144215385645566,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42142495511264777,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49708063531780444,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33296735510279596,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4176386300927819,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32522259162581857,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3572499606049779,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3449668516380805,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4341194278942322,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.36161896085795575,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5052818563161547,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2798191316489921,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.31866179281073254,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3170440263520106,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.45327673850268096,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15538140800156827,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22365453282977818,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1352815632479558,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2610624350708668,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.35907597395908514,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.433310273977633,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33498522957587384,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4529680464694055,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30675389390381064,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49190118767827684,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13922661372145656,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.27553494979330584,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3515170550015674,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.37881852198491145,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30950829536527374,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3839157172568008,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.22141947821999777,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3633108862011865,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2957849631521743,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2872269269040579,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19474118932727338,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3257294949902081,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.26505727008662233,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41342120940573923,
    "sentence_nr": 15
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5489548889989204,
    "sentence_nr": 16
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5292552311493306,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.43141660874998483,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4251732952639193,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.479859141564773,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.47978767796651084,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2751349202729036,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.311148395820729,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5435154526669127,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5395341377171525,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5777979902630328,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6331337405946555,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6121338866063298,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6222767269627676,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5440627210252523,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5801365308278273,
    "sentence_nr": 16
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5097049681318312,
    "sentence_nr": 16
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5622473457673939,
    "sentence_nr": 16
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42567378467735034,
    "sentence_nr": 16
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.470165978205223,
    "sentence_nr": 16
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.47594607773277786,
    "sentence_nr": 16
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5363851621507516,
    "sentence_nr": 16
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4533373633026252,
    "sentence_nr": 16
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5042718376547173,
    "sentence_nr": 16
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8509306641805077,
    "sentence_nr": 16
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9162670716850285,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9682566771439106,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9779127328168863,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7040822331405046,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7673268835807536,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8509306641805077,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9162670716850285,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7639225615341296,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8135226479972402,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6729400620282456,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7157738382386983,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6736973998414632,
    "sentence_nr": 16
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7157738382386983,
    "sentence_nr": 16
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7640211005075139,
    "sentence_nr": 16
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8179683170395244,
    "sentence_nr": 16
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8509306641805077,
    "sentence_nr": 16
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9162670716850285,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.43141660874998483,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.45005622460103567,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5269212212163125,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5528502361092263,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6736973998414632,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7157738382386983,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33491174038847354,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3646077683106875,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.450293182440332,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4822292034174927,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19834633509680927,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2712763621688402,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.546749262754264,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5830342194369027,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2754139367364165,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.34665831783057166,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42877544777223947,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43803970127356867,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.43908893511874636,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4785460996828672,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5898466143484524,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6611594562951559,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.44701416909786756,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5245065297475329,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.31417347869916407,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3530975487930333,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6373258340947424,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6437421244363288,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4715455630189013,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.543275675805182,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2807304798995431,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3418543172008782,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5397682182130759,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5703951757357331,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5446420954986508,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5662782206307382,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3378721588486122,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4362453299175689,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.49288474585647657,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5578180330951528,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.36197274748300795,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36134314178088084,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17060055774694924,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2566677182784047,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5717883675148524,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.640780099960748,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.221071468018936,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.41620491059292214,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4263215396273059,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3711481893609263,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4101392170618868,
    "sentence_nr": 16
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7838756540325346,
    "sentence_nr": 17
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8813081534414112,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6486802664285581,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8066891982024211,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7344798528986015,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8855631322316195,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6486802664285581,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8585894188661937,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7838756540325346,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8813081534414112,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8434569599214109,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9123500588239437,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7849324644314795,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8934780380564308,
    "sentence_nr": 17
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7838756540325346,
    "sentence_nr": 17
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8799941663695641,
    "sentence_nr": 17
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 17
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 17
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6809354000776107,
    "sentence_nr": 17
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8640242853252401,
    "sentence_nr": 17
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7838756540325346,
    "sentence_nr": 17
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8841725044915145,
    "sentence_nr": 17
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.39503194300684213,
    "sentence_nr": 17
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6916289318228928,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3094285625931604,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6328843883953666,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30888995556875376,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6801864286113619,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5512199399393973,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.45862256824436665,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7660160731572102,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.47770079267358434,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8053780976175922,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6259358824502687,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8067950339997761,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5296344689827603,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7183083787484315,
    "sentence_nr": 17
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7568440125092788,
    "sentence_nr": 17
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8347576899702969,
    "sentence_nr": 17
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3001800600660342,
    "sentence_nr": 17
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6794930944968381,
    "sentence_nr": 17
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18879642915927602,
    "sentence_nr": 17
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6584653291380502,
    "sentence_nr": 17
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4697979053121435,
    "sentence_nr": 17
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7554660353280213,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3164389365959547,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7121929522648841,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6031798395521694,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7819677495994619,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5646631238098637,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.836206348617966,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.36615107686578496,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.696074520676609,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1543252261021413,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4932064977882042,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6966863379186454,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7941296295595748,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5487584440377526,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8692797308530646,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8787142254774354,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.944457825946867,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5463887965663883,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7033378749149323,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4912217876159168,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7991339910300419,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7251215108320924,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8334871013677937,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.587725019570444,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7957550794048827,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.28856268147560865,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6187787024786685,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4402122771181734,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7716344099519011,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18465966669442654,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.503938463452404,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17973438065210462,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5509051817440759,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4809103179432793,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7499547288317748,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6244070585346295,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8433626077474702,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.43660156107563336,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7165816705519701,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3748533897614559,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6863935447402433,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3607442374649342,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6876955247522804,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3718491333506089,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6941552634040441,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5110976370499285,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.842915559657988,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5591535564944223,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8079980831297509,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11809858631445573,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5943886568930294,
    "sentence_nr": 17
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1423170365140828,
    "sentence_nr": 18
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.38605131339325,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3230989128220882,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13860487750886114,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36659667376085786,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36295227908523897,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13860487750886114,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36118801210741663,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.40877861250593944,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16673024281943524,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3975048254243706,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11262865194228103,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36030161445252334,
    "sentence_nr": 18
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3066941236048102,
    "sentence_nr": 18
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 18
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.409404483413751,
    "sentence_nr": 18
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3629681915617596,
    "sentence_nr": 18
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12162779391619735,
    "sentence_nr": 18
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4136500403395244,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1909693288724605,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4115524982336727,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14192760409508295,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3989311390496819,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20304460086424203,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4966336271433132,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3935462418730863,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.33523829330170474,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3250861966671464,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3051626462022859,
    "sentence_nr": 18
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30944349609311117,
    "sentence_nr": 18
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11556522074454477,
    "sentence_nr": 18
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.372688132616477,
    "sentence_nr": 18
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.22392361812003433,
    "sentence_nr": 18
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.460938469666163,
    "sentence_nr": 18
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10704943109718215,
    "sentence_nr": 18
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.362953271903766,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14392660099814805,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.376362134090542,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11718316363212337,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3844506520287143,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4024646900219184,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.08197539732074254,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.35287478964221025,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3502198678697797,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.376636825008991,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30372034137078635,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21481172921264619,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4009028477501074,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15065778147399764,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4580508275161034,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21281360709834968,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4292702902558381,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13780534982274106,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3273034480518148,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36078900962911326,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2491467453273127,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.47986445165634506,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10905122148101043,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4502571446121065,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.274959074733397,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3607206140473947,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17796237395371306,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.48209511527864385,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13644487773607678,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36491236604183974,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21850577875478958,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4494281444270959,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.31361999490423276,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1222354265296326,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3727252294250617,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1109484758001971,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3612426584883393,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20356858406857398,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.46358366365120834,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11530762783711283,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3781690117672006,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11907182322580316,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49599003474365394,
    "sentence_nr": 18
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4220964985804286,
    "sentence_nr": 19
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4455062898838481,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32026140564476524,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4016870075045671,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.34697616124581016,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.40373943351486685,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4184617303786878,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4321132548050678,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3499900041521066,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3822330369569219,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4220964985804286,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4455062898838481,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.41428013900466737,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.425713879206717,
    "sentence_nr": 19
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4184617303786878,
    "sentence_nr": 19
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4321132548050678,
    "sentence_nr": 19
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5102296603076779,
    "sentence_nr": 19
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5412065437629714,
    "sentence_nr": 19
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32282559495424096,
    "sentence_nr": 19
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.38266426308756574,
    "sentence_nr": 19
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4230074457298372,
    "sentence_nr": 19
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4432451111759523,
    "sentence_nr": 19
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6363676859401174,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6744544901797789,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9271746317040298,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9736668125871423,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6986939462620247,
    "sentence_nr": 19
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7821077250864037,
    "sentence_nr": 19
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9184678024441792,
    "sentence_nr": 19
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8884834862973964,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3797391466432489,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3481158447116987,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.31102805827817165,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3375837027261476,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19710660977672484,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2646181750020499,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3797391466432489,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3274816319655301,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.28493958837889694,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.35876163607595707,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2485364833746714,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2873862688213756,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.41664461891968263,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.42600414573009276,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2710684964643971,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2982841390442802,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23005567239800093,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.29184715566281483,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2741455993358603,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36403543443534025,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.34279101776553306,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.42600414573009276,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30955822779938535,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.39546682876478195,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.39475108115635776,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.42154888635191134,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2781617026804374,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.32302333182207527,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.08473168573832755,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.25650903369815853,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2883871807684295,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21660761852515356,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.25414220830184964,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32910644083871465,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.29306886812256966,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18084108219203518,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.27583433958197495,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.25612947694888455,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3002607987321696,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3216291288446239,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4272249853925079,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.188590266789637,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.26177705380820604,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3308736026652116,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3875427536757155,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.28432597056103653,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.35944124408933287,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23631465024334478,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2692006325646732,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.259615032947222,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2855780701161316,
    "sentence_nr": 19
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.31343233007308363,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28662182336952924,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.289946670354745,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2585958231966256,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1574562620502688,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2833933092608246,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2330649391612961,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2858508520944113,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17248469309075373,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3673041887389201,
    "sentence_nr": 20
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28838937143148047,
    "sentence_nr": 20
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.25480888745972646,
    "sentence_nr": 20
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14839290005301392,
    "sentence_nr": 20
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.29565285341782266,
    "sentence_nr": 20
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22266775943086,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10508106635796587,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2504422832248121,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22563365567811913,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12913533075470382,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.24776496881674256,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.08680476715745516,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22066482174709295,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12117880855911824,
    "sentence_nr": 20
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.32137825349405363,
    "sentence_nr": 20
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20104685618767446,
    "sentence_nr": 20
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.25137213099939626,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28372673673489807,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.164799256779143,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.32187376249458133,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2969522070783606,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14440617372843148,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.27200704330334224,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2442053369522631,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.33050427873462274,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2133219421911448,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3424665224706109,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8944054777319608,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.24197054442617688,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21682999057776514,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3722897460532404,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.24424323100599224,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2205591704292585,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3479467223515336,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1926917267834754,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4545444680350158,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.17580772500133016,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.32957763052496886,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2148084015365523,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.40974307981059804,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.29622141199363383,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.24146688269469918,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09958408398703665,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22890983822248492,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20795712301883962,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.282761705091657,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2551114536415265,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18112053860965763,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3266298821510716,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1423412184218882,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.26467729752192487,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.286072901441292,
    "sentence_nr": 20
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2851456053265138,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.09858834583812252,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7445389400758123,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9134769668037408,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2506297252541463,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8320381765431424,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9129044064886581,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.23443139907396643,
    "sentence_nr": 21
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.29972668857564216,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12409597120849801,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2928237514438983,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15083364266523736,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.38662429787924074,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22849324967229787,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.44152236347960977,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2989569143807341,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4042166909648807,
    "sentence_nr": 21
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3423939053207622,
    "sentence_nr": 21
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.17611268473423294,
    "sentence_nr": 21
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20441543914149457,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18928624746011372,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43639616127375797,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.29213008358451265,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5828788445270403,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14679869139754204,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4021419566569229,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.329340597116918,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6347143291802012,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2868708266227936,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5779499593492363,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3436610762802303,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2782087319667435,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.632418768195088,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3083012995502152,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6392851743718383,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23050898626566632,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.48172150010681464,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1969221590285716,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5644899370701738,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32594818888335836,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49646222671189383,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4604008032403599,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7444026788985108,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.29161716271402766,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.47302621872495865,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6854823532900025,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3546725638586892,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21468316165048362,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6851126041819388,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.250737833894674,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.40017617077306594,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.27204995504877727,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2743963944428051,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6341922683775969,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7252122374710612,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12586347848916266,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3554854950683664,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3889045463729729,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20229280648000492,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6194717199605934,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.31114459650134146,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11856660123276004,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.34601719602607445,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.40072710492884706,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7206046648616748,
    "sentence_nr": 21
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.22174147515312165,
    "sentence_nr": 22
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2117279815687756,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33999170096577974,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.29221353951377876,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3058731661111107,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2747352174231836,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42736771185803385,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.39727964545172,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10975022749274138,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.13904829787402162,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2873518361947954,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.24505805183333226,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33495074569972355,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3454509072842772,
    "sentence_nr": 22
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.43090467385890824,
    "sentence_nr": 22
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3813511699401743,
    "sentence_nr": 22
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 22
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.22765977642995502,
    "sentence_nr": 22
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2247283208344801,
    "sentence_nr": 22
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30931906627981315,
    "sentence_nr": 22
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2527893205238235,
    "sentence_nr": 22
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9210500207490827,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9069369532463243,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4607778969984477,
    "sentence_nr": 22
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8103868370118212,
    "sentence_nr": 22
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4885014761119101,
    "sentence_nr": 22
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.827819363745503,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17903870455040152,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18440575845606422,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1981763713215807,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2520139548059959,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17499310607879404,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18175908515502465,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10089587713517954,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.11552870044063634,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3168035112884022,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30580678632835573,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10825039887617824,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1278708456868984,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.29705138694670025,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2780223931578523,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18986262747887736,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18230825914917978,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42442305789888696,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.42734795538422576,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18781316135387768,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.16808430602651067,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3454156644973841,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30446460704247824,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4479597674250984,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41132840401983517,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10704445941620296,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.13527356658034445,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09941527806251362,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.13609735884978696,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19230259308735756,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22211286692050705,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20383889880388334,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.17813562619757226,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2986551380628858,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30308773908860176,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10536111661637193,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.13679626017050403,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19732230687816163,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22765162763479738,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3987203877706927,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.39992851145514274,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.09467800236923245,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11434380596647938,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.15034676904545285,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.36138016740101575,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.31224382417562974,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.345966570287759,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2816115803298224,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3461146475963348,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30131374176129855,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1552102601937674,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1381803727119777,
    "sentence_nr": 22
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4967067363118649,
    "sentence_nr": 23
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6330776418175281,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.39501632817024007,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5629116515332234,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.44774758283371513,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6323151453499094,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3353166764160673,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5279751808070301,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3340392563357978,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5542299582982266,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2288355034549531,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.469883747317403,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5472915485853102,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7136367183558585,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6159995640523437,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8398584608765305,
    "sentence_nr": 23
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5155625728615272,
    "sentence_nr": 23
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6435263800797054,
    "sentence_nr": 23
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 23
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 23
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 23
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.32206162101132135,
    "sentence_nr": 23
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.24125880497129865,
    "sentence_nr": 23
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.47825499190432214,
    "sentence_nr": 23
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3292010361291119,
    "sentence_nr": 23
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5670300297444607,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.46086624699736534,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6510894943437193,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5511532346688224,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7550305399541021,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.34537865578685034,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5956718372193373,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.39080227521872696,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.621048393466749,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2755396296659942,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5033588333252278,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5795086255869999,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7183582779188291,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6214211316495574,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7844755306149331,
    "sentence_nr": 23
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6008383045972477,
    "sentence_nr": 23
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7291842011448325,
    "sentence_nr": 23
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 23
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 23
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 23
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.25418196696822093,
    "sentence_nr": 23
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 23
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5117784549266909,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.274941620352113,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4651004879148919,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.22743363869750483,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5634710936922129,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.518836150464752,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6242496691584447,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5989032124636781,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7291306908177887,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2677353447271197,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4460422364967209,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3558785149067877,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.570837784052645,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2624310277292268,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4915471393606767,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.28489318277723963,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6000278331909762,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5728668995816387,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7460634178179616,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.46086624699736534,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6510894943437193,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.46507550803536196,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6687857543858925,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5155625728615272,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6435263800797054,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3639412530979476,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.654342605671994,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19882981891203355,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.45714526865696425,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32269274420690436,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49704406859630557,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42849655626964983,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.662646931303495,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3937441173550755,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5600824723479425,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23114663823833642,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5107406700140826,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.419793811546288,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6152785242440109,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.46086624699736534,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6510894943437193,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.46507550803536196,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6687857543858925,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2296660762967038,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5259172094145851,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.39501632817024007,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5505822266189535,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3215000448278979,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5947774549102596,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20870371467330825,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.40726160697608454,
    "sentence_nr": 23
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3460579711860666,
    "sentence_nr": 24
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43910565102067395,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16692770661327389,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2940239540182693,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17589867762235817,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2991014535844428,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15568794672327907,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30284457998681635,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17340302865304977,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28581037214602456,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1782509297990519,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28710039249342334,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4901491669500622,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5638035394617603,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3460579711860666,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4260473803699743,
    "sentence_nr": 24
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2011131382865372,
    "sentence_nr": 24
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36314253622836745,
    "sentence_nr": 24
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17598839092477797,
    "sentence_nr": 24
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28650792027744043,
    "sentence_nr": 24
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 24
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.15997462319973554,
    "sentence_nr": 24
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.24731742205813823,
    "sentence_nr": 24
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3980108204104697,
    "sentence_nr": 24
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5611872124508993,
    "sentence_nr": 24
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7431443902355421,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4465866985385432,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6260699913485588,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4465866985385432,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6260699913485588,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.25509991414681377,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.505614827211273,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21452424426866915,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.44780791445343104,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23857086413632697,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.47971483823439903,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.446411600799131,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5816697577563045,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4664526119731094,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6399376431552989,
    "sentence_nr": 24
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20156032858716424,
    "sentence_nr": 24
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4855075115512445,
    "sentence_nr": 24
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1526900266679129,
    "sentence_nr": 24
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41716995830580594,
    "sentence_nr": 24
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 24
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.23259933287371404,
    "sentence_nr": 24
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20835831728362864,
    "sentence_nr": 24
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49812931259693377,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17334119484500185,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.31463785312250736,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12522096513057643,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.335302418196347,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9100527513271326,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9584484214161733,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20156032858716424,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.35007862377558696,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3449632275226908,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5000457205552167,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15568794672327907,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30284457998681635,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1529699053146309,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.35702516223197556,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.15975615838102766,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16928451900289662,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.40173762794247314,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15568794672327907,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30284457998681635,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16038844415635037,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30359085570641314,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3595283251171754,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5790446318474887,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.20563705341552085,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3762774944524412,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16692770661327389,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2940239540182693,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14165832410287266,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.24107149684266257,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1258646065963102,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.24857006332411635,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2519649154562495,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.44974180175388206,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3253958243003269,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.45173371737296786,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.27618177741751665,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4305107132988055,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1683625745315614,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.31167225759119427,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.13728361101885644,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3436250633828196,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16353712933127018,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.32934735468962634,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.48680589893384085,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6190257724123215,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1551293035275564,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2674082220133274,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.26091874007348304,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17598839092477797,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28650792027744043,
    "sentence_nr": 24
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1332399603607437,
    "sentence_nr": 25
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.19971937750838645,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1834283688193615,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22588088032876846,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12425342874478343,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1660533764831914,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.15538689193055893,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14158209035366248,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1869416235999822,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0578819658044546,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16170596160446446,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2206817446345091,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14914968848461002,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21702090583674813,
    "sentence_nr": 25
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.138685682297543,
    "sentence_nr": 25
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1258687317121735,
    "sentence_nr": 25
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1327332961698289,
    "sentence_nr": 25
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23556366957615363,
    "sentence_nr": 25
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22894370639738668,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16684195647378827,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.21420692177337528,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33150414660895594,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30808679013173407,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23556366957615363,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.25521078373566897,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14257880024595157,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1979524022915653,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14257880024595157,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1979524022915653,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.260711748598298,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.28143225165615565,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.25621420675166556,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.32613185963061736,
    "sentence_nr": 25
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.21310996044302127,
    "sentence_nr": 25
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2620829676028965,
    "sentence_nr": 25
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.08892786873926031,
    "sentence_nr": 25
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.14069122234920528,
    "sentence_nr": 25
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.12273033502938982,
    "sentence_nr": 25
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.15070376710164984,
    "sentence_nr": 25
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.17376029392152273,
    "sentence_nr": 25
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.22421987263715565,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.07369293827420972,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.08728042965046878,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.12416744870990627,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.06452498627127952,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.09758509152849626,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.09985298970743903,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.22158794642706012,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.20787168962643957,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.05401240601013853,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.07243671671799473,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1543646468773244,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09348998462584433,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.130990604448226,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09885362316286796,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.15900429623613993,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.10903227170832805,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11481934989482791,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1745453831609756,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.046916282267844764,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1250076305588977,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.12985392271660248,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.06737080019124615,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18629057860741663,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1504281768235603,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.11099491388125307,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1201070010200949,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.08702826664587757,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42262353460370816,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3966051357904673,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.09612004569821603,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10249207815381514,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1341907303110576,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.11635402454082566,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.1636348970852316,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.06028131279303415,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0901676620993871,
    "sentence_nr": 25
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6983671476675032,
    "sentence_nr": 26
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6697193437120026,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5809024483660724,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5409616569206442,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5893051076561628,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.555242666304663,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5197038614969076,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4944106522194635,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5863087308455573,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5756247354842696,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.44763438063632005,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4327706284829231,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4562933372999328,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4354000091116894,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.650945489442927,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6025447507087655,
    "sentence_nr": 26
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5040260890269513,
    "sentence_nr": 26
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.48159079549233025,
    "sentence_nr": 26
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3966338449810425,
    "sentence_nr": 26
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3940867714969907,
    "sentence_nr": 26
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3186669369694382,
    "sentence_nr": 26
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.34867169182256896,
    "sentence_nr": 26
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6350785093832516,
    "sentence_nr": 26
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6188888500556722,
    "sentence_nr": 26
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7997394936755756,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7811228513409922,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.9660854289024723,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9613867167137871,
    "sentence_nr": 26
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7158159753911548,
    "sentence_nr": 26
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7127947486849641,
    "sentence_nr": 26
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6813410498464633,
    "sentence_nr": 26
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6671821168913319,
    "sentence_nr": 26
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.45066539224706753,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4254592023616511,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.45779216736532874,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.40945502186629257,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.40071581088356767,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36844216279073794,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14609848125563302,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.18504017619904287,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4184317523303411,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.40500270963162277,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4125433652059801,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3955923992862865,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.47182538941865537,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.42450279333172475,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.46492333059956836,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4401112788616263,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3967795858478363,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3803134453035716,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.34915707707242977,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.34988691421168616,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2613611691981996,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2740054517113319,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5600863252474344,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5179797138258272,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3461243385522883,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3560268535895035,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.43650008892828823,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.42551924250056755,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.504580863725975,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.46703102558879955,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.36954961729302616,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.34760122558190465,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3803026331533805,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.362200056491149,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.24777987943516128,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2952194113831596,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5258092834799059,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4981801549352249,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.48625052891235754,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4290939038872796,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4045007320789693,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4098113348256027,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.44158642009003995,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.40903259597127894,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4946406341236379,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4719975064311173,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.41182432358851845,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4034715718148006,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3693186725771347,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.36304188784855995,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3692675983091899,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.37402683054534963,
    "sentence_nr": 26
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7645786047678913,
    "sentence_nr": 27
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8655501219338723,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8643729226327672,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9215030582508996,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8643729226327672,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9215030582508996,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7858164289172753,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8872272977237059,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.8643729226327672,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.9215030582508996,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6898913050782208,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8620687741940413,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6898913050782208,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8528837782425732,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7708719635370461,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8793197587693242,
    "sentence_nr": 27
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7708719635370461,
    "sentence_nr": 27
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.888538633093067,
    "sentence_nr": 27
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6840689169974626,
    "sentence_nr": 27
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8314419144081646,
    "sentence_nr": 27
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5819799380263497,
    "sentence_nr": 27
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7407958979814505,
    "sentence_nr": 27
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7645786047678913,
    "sentence_nr": 27
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8655501219338723,
    "sentence_nr": 27
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.41098733201100757,
    "sentence_nr": 27
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.651283133493195,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6152755816095169,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7669297251133314,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4250002996145258,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6670552714553488,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3735617779670567,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5773479111816255,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5543498698280007,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7266847297604082,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3716332023564544,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6132388888021502,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6986939462620247,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8497711598086016,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5072570733389083,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7124868368374351,
    "sentence_nr": 27
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5907596734005102,
    "sentence_nr": 27
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7837270250239556,
    "sentence_nr": 27
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.10008881112800158,
    "sentence_nr": 27
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.29125356488795046,
    "sentence_nr": 27
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.0,
    "sentence_nr": 27
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.041649157343430596,
    "sentence_nr": 27
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6587480145435196,
    "sentence_nr": 27
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7917841426705801,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7446828000198126,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.885521980076414,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6466833757622275,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7737914417145209,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4447278656331358,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6742569711624775,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.600047216971444,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7511423755179258,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3382340617900419,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6182585373365673,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6069548573053054,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7630436854704967,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.40482952759410495,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6241130944295542,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5021718181363274,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.697189669759932,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7858164289172753,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8717639062922423,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5731680012014568,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.746935173521359,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7224037170215811,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8452672523905139,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5724496367057007,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7350859720106757,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42250552136302394,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6425389837629188,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7645048342610411,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.876234192352485,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.45751787171307623,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6647794363792763,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7623067286250759,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8682092620191191,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.46189821859121283,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6442319235751083,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3931991982536581,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6422735790483707,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.44644290381704027,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6892051604181435,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4000177797533498,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.645169701736652,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4479818542603719,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6761961025641056,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7123871749204508,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8331784519293958,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5749089871602278,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7211428196508521,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.38506289173931413,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6152360906748179,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6231488481063673,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7734960210241439,
    "sentence_nr": 27
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4460616097899727,
    "sentence_nr": 28
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6833569517560225,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4460616097899727,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6833569517560225,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4460616097899727,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.693261298341864,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4460616097899727,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.693261298341864,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6745016003476486,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8511670783317596,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32329508170352383,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6141330847741713,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4460616097899727,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6833569517560225,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3837983925863447,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6366757448341102,
    "sentence_nr": 28
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6745016003476486,
    "sentence_nr": 28
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8511670783317596,
    "sentence_nr": 28
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 28
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 28
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6667025833042813,
    "sentence_nr": 28
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.746973053424487,
    "sentence_nr": 28
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6745016003476486,
    "sentence_nr": 28
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8511670783317596,
    "sentence_nr": 28
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.217554942150074,
    "sentence_nr": 28
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4859163400220353,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3008656294855478,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5198655773563042,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3008656294855478,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5198655773563042,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.203264842568494,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4965705242699611,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32079058840140134,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5094305382960898,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23693055763743093,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4968400811224627,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32079058840140134,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5094305382960898,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.35479105265934485,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4725761870926308,
    "sentence_nr": 28
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3301899334885226,
    "sentence_nr": 28
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5632801217523468,
    "sentence_nr": 28
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 28
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 28
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1923904871441659,
    "sentence_nr": 28
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5825915593253297,
    "sentence_nr": 28
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.32079058840140134,
    "sentence_nr": 28
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5094305382960898,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4892199210635081,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6263002679299042,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.09147827112247602,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3360691966057836,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2966218714191134,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5348497180679597,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3008656294855478,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5209701084013916,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3254074668234594,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.540582703782851,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.22935466869603194,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6357138961264384,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4460616097899727,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6833569517560225,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.38769943713308697,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6179897670313796,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.35964066074252593,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5418421848087059,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.31666472263798334,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5096984883597744,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2656621439255861,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.47187800221660153,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.41583634222861793,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6558319092753532,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.26633048164380024,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5038200170930055,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5371525807924681,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.7677378485184402,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.15274299622833287,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4692950277268683,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.30626101600123445,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.583891679561264,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.18137691349228668,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4586072719105437,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.23443677523946913,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5163278972706644,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.33876931708826047,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.550413577565279,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14207405313947058,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.47874702297210975,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2539342198718324,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.46375067718601715,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.200726550812963,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.41645295439394076,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42995245074388394,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6515566568079457,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2834052290575623,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4974109921343301,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.19454290935168927,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49909763892228687,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3837983925863447,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6379993550810827,
    "sentence_nr": 28
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1481394578697113,
    "sentence_nr": 29
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.30063818852404856,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14216645907653844,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.2737034564138708,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7778111223054219,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8190064480412373,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7778111223054219,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8190064480412373,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7778111223054219,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8190064480412373,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.14939354788683526,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.29041654772860626,
    "sentence_nr": 29
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7778111223054219,
    "sentence_nr": 29
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8190064480412373,
    "sentence_nr": 29
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 29
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7778111223054219,
    "sentence_nr": 29
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8190064480412373,
    "sentence_nr": 29
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4125519163596689,
    "sentence_nr": 29
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5539867049403877,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5420662441541858,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5445089463670787,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.40919282596076484,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5542936932152527,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4125519163596689,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5539867049403877,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4125519163596689,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5539867049403877,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5928902071159559,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.647817438132439,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.5928902071159559,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.647817438132439,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4125519163596689,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5539867049403877,
    "sentence_nr": 29
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4125519163596689,
    "sentence_nr": 29
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5539867049403877,
    "sentence_nr": 29
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.34641959937802264,
    "sentence_nr": 29
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.47549559716182727,
    "sentence_nr": 29
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4125519163596689,
    "sentence_nr": 29
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5539867049403877,
    "sentence_nr": 29
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4125519163596689,
    "sentence_nr": 29
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5539867049403877,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42461633178803443,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5603699277937889,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42254876310519374,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5561399558171133,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2340216139262901,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4522093023662336,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4132352454218328,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5544725906870476,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42254876310519374,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5561399558171133,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3951500216160541,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "translation",
    "metric": "chrf",
    "score": 0.6089660957340174,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42254876310519374,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5561399558171133,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42282359171428024,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5395092365663595,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "bleu",
    "score": 0.35412968165085734,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4985795126785612,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1598921499894403,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "translation",
    "metric": "chrf",
    "score": 0.390187618292215,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2400540439585043,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "translation",
    "metric": "chrf",
    "score": 0.49297433772099697,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4806604068305994,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "translation",
    "metric": "chrf",
    "score": 0.664228268001068,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42254876310519374,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5561399558171133,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2340216139262901,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "translation",
    "metric": "chrf",
    "score": 0.45184273575809186,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.7778111223054219,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.8190064480412373,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "bleu",
    "score": 0.16533113836624475,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4074791764578974,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "bleu",
    "score": 0.28547397706062927,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4838477808123968,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "bleu",
    "score": 0.6053011982655683,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "translation",
    "metric": "chrf",
    "score": 0.652613765735072,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "bleu",
    "score": 0.4229247984636106,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "translation",
    "metric": "chrf",
    "score": 0.556465536088555,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "bleu",
    "score": 0.42254876310519374,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5561399558171133,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3471790743028735,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4458106286047354,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "bleu",
    "score": 0.3555508425572384,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5387745992013905,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "bleu",
    "score": 0.1709686260975486,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "translation",
    "metric": "chrf",
    "score": 0.3940091304204109,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "bleu",
    "score": 0.25958657290343434,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "translation",
    "metric": "chrf",
    "score": 0.43162699627918094,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "bleu",
    "score": 0.2213908395073965,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "translation",
    "metric": "chrf",
    "score": 0.4213527844474163,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "bleu",
    "score": 0.39696685122270786,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "translation",
    "metric": "chrf",
    "score": 0.5497060467823045,
    "sentence_nr": 29
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 0
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 1
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 1
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 1
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 2
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 2
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 2
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 3
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 3
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 3
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 3
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 3
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 4
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 5
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 5
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 5
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 5
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 6
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 6
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 6
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 7
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 7
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 7
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 8
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 8
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 8
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 9
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 9
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 9
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 10
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 11
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 12
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 12
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 12
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 12
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 13
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 13
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 14
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 14
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 15
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 16
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 16
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 16
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 16
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 16
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 17
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 17
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 17
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 18
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 18
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 18
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 18
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 19
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 20
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 21
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 22
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 23
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 23
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 23
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 24
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 24
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 24
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 25
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 26
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 26
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 26
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 27
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 27
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 27
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 27
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 28
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 28
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 28
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "classification",
    "metric": "accuracy",
    "score": 1,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "classification",
    "metric": "accuracy",
    "score": 0,
    "sentence_nr": 29
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9411583614202783,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9389202454786235,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 0
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8775848642818888,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8618703443763697,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7861888156926622,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7987489460131649,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9319748402595084,
    "sentence_nr": 0
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7613425680699503,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8493237569441244,
    "sentence_nr": 0
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9020031517329425,
    "sentence_nr": 0
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8493237569441244,
    "sentence_nr": 0
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.883570112979728,
    "sentence_nr": 0
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8263460336753243,
    "sentence_nr": 0
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8060322164809728,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8980680846396624,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9491059403137463,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9664300701360793,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9457224261353452,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9708225134054753,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9419324607589119,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9619002332717353,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9189927159116271,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.895905738615658,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8719916488298841,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9397108105925289,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.884345665982421,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 0
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9584454525436005,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9643081480127652,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9067144042813564,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8781616442886918,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9745733081082687,
    "sentence_nr": 1
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9237743711831492,
    "sentence_nr": 1
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9659571253320222,
    "sentence_nr": 1
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9044755244774213,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9016506657203592,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9259203238585231,
    "sentence_nr": 1
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9226314544302758,
    "sentence_nr": 1
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6237003645369218,
    "sentence_nr": 1
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.919365977563579,
    "sentence_nr": 1
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9113270242697518,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.898943894327586,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9736119227904283,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9415432301630186,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.973004167300919,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9617726716367615,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8788632576179716,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9442690941930104,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9167527970009353,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9264966822048945,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9760432643638268,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9290639912797567,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9451284616565533,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9571970948049097,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9428452278208271,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.924510998540744,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9354255661287414,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9038448099971822,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9290214610132344,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9359307328554756,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9462257677914746,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9685511109758306,
    "sentence_nr": 1
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9466350739636148,
    "sentence_nr": 1
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7785501063601203,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8677672451180615,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9519685270619841,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.5524309559543085,
    "sentence_nr": 2
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8979970994003059,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8979970994003059,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9598023304313453,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8678877090803476,
    "sentence_nr": 2
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.3628854370408249,
    "sentence_nr": 2
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8866932684030095,
    "sentence_nr": 2
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7932574787392968,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8840632918991035,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9244224424282228,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7493760739956499,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9434070582654602,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8626111481890223,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9742381587466754,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9614829239512629,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9634058264556766,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.846746937646691,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9416090102549223,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9586487245465463,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8628736669093499,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8883148663773122,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.921000444185013,
    "sentence_nr": 2
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 2
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.964284245003951,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.899852954654377,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.5884852453065169,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8943359440390058,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6239646156236577,
    "sentence_nr": 3
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8782485779028959,
    "sentence_nr": 3
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9219735185328113,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8379214027434272,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9171135147465285,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8793006100154936,
    "sentence_nr": 3
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6764135013792538,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8320911917964368,
    "sentence_nr": 3
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8320911917964368,
    "sentence_nr": 3
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 3
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9020259333664543,
    "sentence_nr": 3
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8443316591536836,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9062739514559724,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9243814194896306,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9257122714800141,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9048929676970495,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9233238051356927,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8961117810241208,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9137011072166213,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9144918070375806,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9447475462972004,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9418568225974095,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8631885674989124,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9540570534869818,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9356691952085903,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8263666332486633,
    "sentence_nr": 3
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9187937618702817,
    "sentence_nr": 3
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6492261286778312,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.4782990117524071,
    "sentence_nr": 4
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8728890059382535,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7924841060781368,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8728890059382535,
    "sentence_nr": 4
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8085699807438939,
    "sentence_nr": 4
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9309167160514913,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8335210974928002,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9407617520385465,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9009704508776215,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.886161550229872,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8864780713525466,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8619950335517561,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.877644990158928,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9473578431592224,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8989284887461744,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8982857165205713,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9421743042333945,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 4
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.909430339396572,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9114715597392106,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9221676855227006,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.903310364652346,
    "sentence_nr": 5
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.43631872104818037,
    "sentence_nr": 5
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.725100223395414,
    "sentence_nr": 5
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8342041754812477,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7541096773855238,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9352893606252747,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7137044016250488,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8459329201101423,
    "sentence_nr": 5
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9155785169978052,
    "sentence_nr": 5
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.454243405917021,
    "sentence_nr": 5
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.4367071875067552,
    "sentence_nr": 5
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9053865214400596,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9344907300105301,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.941467473244312,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8759462570863868,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9116059567890715,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.95453015576562,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9271804273091313,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9494380676747487,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8907525765155897,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9420326057327402,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8729192735278123,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.840210783941434,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8830406923187026,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8705872791986208,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9129896861855028,
    "sentence_nr": 5
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 5
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9775140091004713,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.931908394385036,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.958499216692883,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9787648208394673,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8848447424869419,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9476480635849643,
    "sentence_nr": 6
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8420296194650692,
    "sentence_nr": 6
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9645398026978572,
    "sentence_nr": 6
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.976975965491712,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9575751193892209,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.917870378110458,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.917870378110458,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.922108923148009,
    "sentence_nr": 6
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9367021384173281,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.917870378110458,
    "sentence_nr": 6
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9136709169732016,
    "sentence_nr": 6
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9031487241080103,
    "sentence_nr": 6
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.922108923148009,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9717329164232313,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9810420842974353,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9296061535584738,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9548717794727779,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9723617284409432,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9433216405879152,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9253992588631311,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7833761650543694,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8958698547783525,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9659983030155975,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9368374793769542,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9292848975349729,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9705333075369675,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9560908971572966,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9288860917142431,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9402643484548583,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9303023646781129,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9076656012518489,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9272618174968876,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9630829363546703,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9437691960187881,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9233897890679653,
    "sentence_nr": 6
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9217593594034571,
    "sentence_nr": 6
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9429459010031568,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9680340601535599,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9444947592571505,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9524237679532525,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8521740000505951,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9147273981117778,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9353915284262971,
    "sentence_nr": 7
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9575256886848735,
    "sentence_nr": 7
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 7
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9544425909905248,
    "sentence_nr": 7
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 7
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.887089742205764,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8937272463225717,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9221577416896909,
    "sentence_nr": 7
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7360571605491374,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9424882191492142,
    "sentence_nr": 7
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9158962896380519,
    "sentence_nr": 7
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9016185053131788,
    "sentence_nr": 7
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9519313199322048,
    "sentence_nr": 7
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9002497361613263,
    "sentence_nr": 7
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9424882191492142,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9404564646985731,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9525612663771642,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9416090102549223,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.946182450185975,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8827665860178672,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9242269657430007,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9209375409360453,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9453162319718537,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9354735336178899,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9650606723493668,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.937172702008466,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9037456319061896,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9527540439558733,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9777992945719618,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9483614149601093,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9630476322301069,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9090634311284931,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9592439701684463,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9352813563171796,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9578898822826803,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9349087092124988,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9553475775967099,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9426144990998162,
    "sentence_nr": 7
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9455357310467346,
    "sentence_nr": 7
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9950087915805451,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9950087915805451,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9359599516797827,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9950087915805451,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8529883661830301,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9313047211019367,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9311406569876187,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9392038901097501,
    "sentence_nr": 8
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9504743930445531,
    "sentence_nr": 8
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 8
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9950087915805451,
    "sentence_nr": 8
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9283998656503502,
    "sentence_nr": 8
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9934034758807603,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9131528589305679,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9917679206284817,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9566767123929576,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9359924521743563,
    "sentence_nr": 8
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8893588081911743,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 8
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 8
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9583698738001583,
    "sentence_nr": 8
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 8
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 8
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9934034758807603,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.946392812169666,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.911875333930421,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9169315433407361,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9541325707307038,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9648123726963476,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8370298547932784,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9334875203861144,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9413496332501932,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9956823103485622,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9457390517164731,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9671298665063969,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9336521523423332,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9502062892893858,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9333019767772176,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9037394051488277,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9283644587512466,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9237582925385585,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8995566191566017,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.896344147038989,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.09821094254330615,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9548273305811203,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9251737690567995,
    "sentence_nr": 8
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9275689564213165,
    "sentence_nr": 8
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9272442008199501,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9520060001290835,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9058859200742604,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8789724147701462,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9137645544850267,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8969027357279203,
    "sentence_nr": 9
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9520060001290835,
    "sentence_nr": 9
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9275374047069039,
    "sentence_nr": 9
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8772309014828462,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9140052999897977,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.868350408637765,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7563541659131354,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8578315979157695,
    "sentence_nr": 9
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8441075622700097,
    "sentence_nr": 9
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.23829288001976573,
    "sentence_nr": 9
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9407267756704489,
    "sentence_nr": 9
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.831845583109951,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9530684796567226,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8984174935165463,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.946008414943598,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9285885624039975,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9645189965938258,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9601667560566091,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9113133701465544,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9363094557613988,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9499594621802195,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8850558582872771,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9413520522974334,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8953760832780698,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9516191368774216,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.873135905690596,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9331628274049639,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9350921637704382,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9398175409358328,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9675093986501344,
    "sentence_nr": 9
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 9
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9282207391671503,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.957452925924953,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8937237551170429,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 10
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9256331955884847,
    "sentence_nr": 10
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.904390835311888,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8995954000535624,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.928962868887516,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9339798045072082,
    "sentence_nr": 10
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8008809042180175,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9240001424211951,
    "sentence_nr": 10
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.3493344613894351,
    "sentence_nr": 10
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.92829327413418,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9359271530286619,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9641555435524619,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.90719289051837,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8543701176038877,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9045960456690756,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9576659929734302,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9445842802137389,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.917893569547509,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9031282594956593,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9325823323160847,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9171277146973622,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9631220314707449,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9125575210703364,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9671298665063969,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8583796678495444,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.917870378110458,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9075511178990168,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8942877287874674,
    "sentence_nr": 10
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 10
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8881782096383685,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8452994228892592,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.857664755026069,
    "sentence_nr": 11
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7687402404428638,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9425182378610694,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8221659843346086,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8685375697135141,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7860944644568774,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7829829019188287,
    "sentence_nr": 11
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9425182378610694,
    "sentence_nr": 11
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.289269703803095,
    "sentence_nr": 11
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7829829019188287,
    "sentence_nr": 11
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9425182378610694,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.915813486906383,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.928671169616198,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9195852720074569,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9260563505342738,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8580715674095071,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8991782906832555,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9549429726485847,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8571447284090962,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.953599772014362,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9382091007325469,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9125682774652475,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9084959093441131,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9389584881035126,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8968120926569282,
    "sentence_nr": 11
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8757339860702672,
    "sentence_nr": 11
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9742989957563788,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9854564066904739,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.938338375356983,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9363458435045497,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9275189832478317,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9680610688075657,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9458276502828801,
    "sentence_nr": 12
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9555270393882619,
    "sentence_nr": 12
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.774972667720128,
    "sentence_nr": 12
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9238483556315539,
    "sentence_nr": 12
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 12
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9292605756517186,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8710905917506855,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8877998658561537,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9408832971568818,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8758560882945217,
    "sentence_nr": 12
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9047504210526172,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9149458726191051,
    "sentence_nr": 12
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9497380252636716,
    "sentence_nr": 12
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9247145535687903,
    "sentence_nr": 12
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 12
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8829314518141973,
    "sentence_nr": 12
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9497380252636716,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9369900232316837,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9584772514045287,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9656526051593539,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9262800142753679,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9178799098053634,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8988056403515298,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9240902217687106,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9454713149117651,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9457650793019858,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9115531547253959,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9403725471773088,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9107758326980321,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9251111872988325,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9267004903727016,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9652440580136615,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.924254800539438,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9054967244578502,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.886673201587762,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9082204179924286,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9665046359304257,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9492870842156111,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 12
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9495327576081029,
    "sentence_nr": 12
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9605742681789634,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9410712595774171,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.971921146040729,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8360964435901039,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9278436686065653,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9540941235545723,
    "sentence_nr": 13
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7765803419515074,
    "sentence_nr": 13
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9368660209060221,
    "sentence_nr": 13
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9179315685239186,
    "sentence_nr": 13
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9198867501155861,
    "sentence_nr": 13
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9357668560693397,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.880651835588671,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9322025130978147,
    "sentence_nr": 13
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8666701669384438,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9301584319196643,
    "sentence_nr": 13
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9201441893603447,
    "sentence_nr": 13
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.4518476286184633,
    "sentence_nr": 13
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8817151383770689,
    "sentence_nr": 13
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9719892276800867,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9232252378020026,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.90340499273861,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9445601279006905,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9284637794790105,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9506720475284802,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9650672132857259,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.935825271074837,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9417006532894496,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9180957642017807,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9336273124319283,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9199623581249377,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9420383150390214,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9169222881606529,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9358954768171188,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9210475526688618,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.900422383617428,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9665042848270522,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9195975724156285,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9482591669689567,
    "sentence_nr": 13
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.894400898846725,
    "sentence_nr": 13
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9683895601588671,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.974733551222386,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 14
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.935724475087967,
    "sentence_nr": 14
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.945278116491169,
    "sentence_nr": 14
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.913976993531483,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9206503738833902,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8879551150411227,
    "sentence_nr": 14
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9093507960484853,
    "sentence_nr": 14
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.44325871778061554,
    "sentence_nr": 14
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8629899790604912,
    "sentence_nr": 14
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8839868610728687,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9659019608247615,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9612040783142544,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9355702448711621,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8575724679460186,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.919154316989783,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9107041155041439,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8860042875765471,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9163443895096822,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9513360683724416,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9506442510575418,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9210869399305139,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8602965545640948,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8912610518101419,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.857937519719319,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9528771181894694,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9241995664234885,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9432104991415542,
    "sentence_nr": 14
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8927784164557715,
    "sentence_nr": 14
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8681309346882299,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9045257596276787,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7552111299277484,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.82396628763246,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 15
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8809116426093319,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9069369532463243,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8255413975339149,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9116712045344968,
    "sentence_nr": 15
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8855094439275503,
    "sentence_nr": 15
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8809116426093319,
    "sentence_nr": 15
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.5085021700346579,
    "sentence_nr": 15
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8155954216287978,
    "sentence_nr": 15
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8849766832597384,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9321985099431636,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9158869153954171,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8940299169999223,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9029209331114941,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9434784706316768,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9504499063681887,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8103402263404181,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9033542015144801,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8920851535963175,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9012698346023688,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8815241253287673,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.955434974676454,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9190034267575142,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9028341607528202,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7933760889502307,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9669111778196173,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9183552099282611,
    "sentence_nr": 15
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9213964969470535,
    "sentence_nr": 15
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9438561056375272,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9245427558640842,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9466217999433078,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8600910973378976,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.5465479162881712,
    "sentence_nr": 16
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.908088143295894,
    "sentence_nr": 16
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8689979953554426,
    "sentence_nr": 16
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8837997874830685,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9430526976186369,
    "sentence_nr": 16
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7213258253735133,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8583796678495444,
    "sentence_nr": 16
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.5352913894873965,
    "sentence_nr": 16
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7506613813658406,
    "sentence_nr": 16
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9120029292560927,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.969258616291086,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9359933426460225,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8446197069920836,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9665537794677691,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7519024768911576,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9419599049218603,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9100379761498075,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9243062555931161,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9232535952320629,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9430158926147498,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8923268998495886,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9316958873367511,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9441083273271286,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.899852954654377,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9451690574618664,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9470556595464068,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8625414653847894,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8658510104009289,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.938651167013012,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9362303281043904,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 16
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9288883358178652,
    "sentence_nr": 16
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7378741057437793,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.898904151376881,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 17
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8446522700991944,
    "sentence_nr": 17
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9053865214400596,
    "sentence_nr": 17
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8700885813654318,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9331139325257429,
    "sentence_nr": 17
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8860497305091617,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8222704990602537,
    "sentence_nr": 17
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8402559609277754,
    "sentence_nr": 17
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7386088026745246,
    "sentence_nr": 17
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.06557474419143802,
    "sentence_nr": 17
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8700885813654318,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8771568927591851,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8869070241487921,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8173012945645394,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8220012279932035,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8449397341788647,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9239069749524619,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8972504357155736,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6602446784708298,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8667833154965509,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7306831212016971,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7306831212016971,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7406377967705062,
    "sentence_nr": 17
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8509760908759664,
    "sentence_nr": 17
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.96926930549605,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8641726957145408,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9637804258017773,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9240863542577373,
    "sentence_nr": 18
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9450374119495017,
    "sentence_nr": 18
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.96926930549605,
    "sentence_nr": 18
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9424882191492142,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9424882191492142,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9392663489644577,
    "sentence_nr": 18
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8389799674466019,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9253208187778743,
    "sentence_nr": 18
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9221577416896909,
    "sentence_nr": 18
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9221577416896909,
    "sentence_nr": 18
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 18
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9144266092886102,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9500117624130617,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.905862662289465,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9003734503251455,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.858544407149412,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9281598514152588,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.948121913854874,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9629589146416885,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9580736862318411,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9708835294542548,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9234823141384267,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9939521304203686,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9474838221026617,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9488355997601815,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9424390135303181,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9711070259637357,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9237920416869381,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8942780008373756,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8468261925085733,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8976119317111001,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9527352893094178,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9510981354135275,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9521144628004171,
    "sentence_nr": 18
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 18
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9774592733638915,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9665042848270522,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9806060444395596,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9049668032095894,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9665042848270522,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9667317239059525,
    "sentence_nr": 19
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 19
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9159800198090925,
    "sentence_nr": 19
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9667317239059525,
    "sentence_nr": 19
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8925738398388144,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9058585844143391,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8888787903169728,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8925738398388144,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9128855680689195,
    "sentence_nr": 19
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9272821491047395,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9413354408985303,
    "sentence_nr": 19
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.46619006556188114,
    "sentence_nr": 19
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.913896513382741,
    "sentence_nr": 19
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9058585844143391,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9557922260754473,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9391656780027514,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9260113686541587,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9419307613884336,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9845996986850503,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9255228522887315,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.889174440461237,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9496761617043387,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9322360743819351,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.935492418630274,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9456325305487512,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9325466173278317,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9240800356922247,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9361690788124847,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.938043640398588,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.901373116210745,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9531605377803356,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9132591460407243,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9494481589794223,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9415361564397403,
    "sentence_nr": 19
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.897450557161678,
    "sentence_nr": 19
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.937002127196651,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9435408381256087,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9421449698305296,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9607456319189528,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.5467617051776391,
    "sentence_nr": 20
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8969209805167669,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9060555921929084,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8969209805167669,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9096430262961498,
    "sentence_nr": 20
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7983940190154283,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9132591460407243,
    "sentence_nr": 20
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9204057102575467,
    "sentence_nr": 20
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.4968312722246179,
    "sentence_nr": 20
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8001971757912975,
    "sentence_nr": 20
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9204057102575467,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.95112146871187,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.949624286506194,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9588139991437585,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9236414681715879,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9453633691396565,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9278367059866518,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9302237306555959,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8441460025255829,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9470556595464068,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.951863030034636,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8944443568631728,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9082204179924286,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.90717359411325,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9014597856352894,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9250084453288043,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.95462554022758,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9318340131711181,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9736147802901586,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9182449217144187,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9400180064454685,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9255769217104873,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9309426923102619,
    "sentence_nr": 20
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9002012094811458,
    "sentence_nr": 20
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9690017425712892,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6924365679057801,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.804543317337012,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8385395593542468,
    "sentence_nr": 21
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9515560914045473,
    "sentence_nr": 21
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.854435717190483,
    "sentence_nr": 21
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7570244995532351,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6676892344393273,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.873135905690596,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6885773376269438,
    "sentence_nr": 21
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.46961217063286037,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8379214027434272,
    "sentence_nr": 21
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7570244995532351,
    "sentence_nr": 21
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.20981645725460496,
    "sentence_nr": 21
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6659995521111991,
    "sentence_nr": 21
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7570244995532351,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8388678282825207,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9180596829241628,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9166274634412449,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8626786769008709,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7991709881281639,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8119656541607598,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8872308158649556,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8914910756561332,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.927494511055529,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9528614248210486,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8523282278495175,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9297633204435644,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9278042759794851,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8998995790099074,
    "sentence_nr": 21
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9302677881301988,
    "sentence_nr": 21
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9522511234396616,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7585159184184324,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8922770448230282,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9126128133576369,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6245412677586388,
    "sentence_nr": 22
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.868233862673363,
    "sentence_nr": 22
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8852329532489643,
    "sentence_nr": 22
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8378994642516495,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8775848642818888,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8493237569441244,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9448292727000915,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8555426729178464,
    "sentence_nr": 22
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7558344174949267,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8497451239178159,
    "sentence_nr": 22
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8493237569441244,
    "sentence_nr": 22
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8199763712080639,
    "sentence_nr": 22
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 22
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8206722459046871,
    "sentence_nr": 22
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.883570112979728,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.914786293186172,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8845568645036501,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8937192042814042,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.901348698020278,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8382013802825361,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9219786709510569,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8767649499531999,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9094880423990607,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8719390074611821,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9349020382990011,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9272997117562144,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8962185446474815,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8930034245249151,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9271664513693498,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8936606750264663,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8803360259381345,
    "sentence_nr": 22
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8680210960657176,
    "sentence_nr": 22
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9699436870249787,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9699436870249787,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7931982206364059,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9699436870249787,
    "sentence_nr": 23
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9438398456065387,
    "sentence_nr": 23
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9281186022380125,
    "sentence_nr": 23
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9699436870249787,
    "sentence_nr": 23
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9184823166209557,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8839868610728687,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8884834862973964,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9300073119656489,
    "sentence_nr": 23
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9381606131991436,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8839868610728687,
    "sentence_nr": 23
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9300073119656489,
    "sentence_nr": 23
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.4072337657555589,
    "sentence_nr": 23
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9184823166209557,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9293646790023864,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9511392272878579,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9293879632586071,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9277950353049101,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8843378183459343,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8741633139531418,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9271525909282003,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9736840552120738,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9396084767892234,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9187563342696414,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8896752045577786,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9737097349915758,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9330058893011377,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9570066548501687,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9201684039669155,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9133901345922595,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9458636432813123,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.917857433142856,
    "sentence_nr": 23
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9375412439691305,
    "sentence_nr": 23
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9556267474396976,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9489054429933926,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9489054429933926,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8327628422929998,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9249365863966041,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.922528755167094,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9486938895906879,
    "sentence_nr": 24
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 24
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 24
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8620685016584069,
    "sentence_nr": 24
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9405916043682414,
    "sentence_nr": 24
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9327915990783561,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.909738029095061,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.909738029095061,
    "sentence_nr": 24
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8707492337114523,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.95883735444933,
    "sentence_nr": 24
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9455007606735264,
    "sentence_nr": 24
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9372630850025364,
    "sentence_nr": 24
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.5983897920478856,
    "sentence_nr": 24
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9299762198228243,
    "sentence_nr": 24
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9302303599426779,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9544609413449265,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9355306533611718,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9432457481338326,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9472285181144658,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.923828763793418,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9224761498105726,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9756278595118478,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9499594621802195,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9544238060448419,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9012364553153411,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8199585012210312,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9280048312907723,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9587462450914201,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8938919301593574,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9507758066685948,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9432005035367906,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9675203656708941,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9303385434730891,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9401106918306472,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9533532275954528,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9274629860503822,
    "sentence_nr": 24
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8926908826740254,
    "sentence_nr": 24
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6224897798032885,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7893575827661004,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9478696521177714,
    "sentence_nr": 25
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7160421907140165,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6217685026572488,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.794919886900137,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8793006100154936,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.5916523997385489,
    "sentence_nr": 25
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.4849269488253923,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7462718113811923,
    "sentence_nr": 25
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8083701726292805,
    "sentence_nr": 25
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.722502153449955,
    "sentence_nr": 25
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 25
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.5544920599877754,
    "sentence_nr": 25
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6853792233736985,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9200538056807258,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9630774769374594,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9143443086107108,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9052744049140443,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9018850910676268,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9142574363760879,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9168431011517528,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9141901633008906,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9317477810881586,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9354759108346813,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9141453314674155,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9550191440621234,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8402328635525613,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.831845583109951,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9092382099397807,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9770044719642067,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9155318202784664,
    "sentence_nr": 25
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 25
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8272309965382391,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7767725512278205,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9373981486656514,
    "sentence_nr": 26
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9579023880929557,
    "sentence_nr": 26
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9268329536813669,
    "sentence_nr": 26
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.904428807825769,
    "sentence_nr": 26
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9116613044583819,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9084279839455062,
    "sentence_nr": 26
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8013174743750245,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.34811585804131506,
    "sentence_nr": 26
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8912610518101419,
    "sentence_nr": 26
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9084279608664247,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9342971539350323,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9618018909441389,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9221850850049388,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9621502301102783,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9207497282487874,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8817316559043479,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9595521389704431,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9604273088099046,
    "sentence_nr": 26
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8832167531630292,
    "sentence_nr": 26
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9618018909441389,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9338423795983638,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8069582822584229,
    "sentence_nr": 27
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9432051372011929,
    "sentence_nr": 27
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8875472267363329,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8538919155402751,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8601111478550084,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8274840531521687,
    "sentence_nr": 27
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8737243337458652,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8875472267363329,
    "sentence_nr": 27
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8213297311895551,
    "sentence_nr": 27
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.3007622907436899,
    "sentence_nr": 27
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.906379768806771,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8996352283472103,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8577239523880982,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9705288278234159,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9022302698191352,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9618116705103616,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9282902444420971,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9283062281157928,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9143841728614055,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9148205155364358,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9429357495928096,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8199038085123204,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9007500710615358,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9335504867261654,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8519148326217993,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9467340802817513,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8914166352994622,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8697448206881571,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9091527400737927,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9487286082082608,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9550331732946552,
    "sentence_nr": 27
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 27
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9703747509928279,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9540941235545723,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9543144589160125,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.652649628941592,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9767775472269087,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9393628940364738,
    "sentence_nr": 28
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9410712595774171,
    "sentence_nr": 28
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.6444379795256558,
    "sentence_nr": 28
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8964898605551818,
    "sentence_nr": 28
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9263597385884417,
    "sentence_nr": 28
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.899546929868499,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.899546929868499,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9256238040654331,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9256238040654331,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 28
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.824741266541094,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 28
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9256238040654331,
    "sentence_nr": 28
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8283905649271065,
    "sentence_nr": 28
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.0,
    "sentence_nr": 28
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.881413837458117,
    "sentence_nr": 28
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.899546929868499,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9437940294094723,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9269703177791706,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.944904344834561,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8479413107328494,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9715595760527852,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8595969327963556,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9538713542813556,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8348508116391393,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9572462820044535,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9375119517314923,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9493167367596885,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9344916654109876,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9849529115133767,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9275259780895282,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9276874028790393,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9473074618830379,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9460494618521745,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8923268998495886,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9455007606735264,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9526558782357073,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9338345156544289,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8995764072227389,
    "sentence_nr": 28
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9505226544098013,
    "sentence_nr": 28
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9630841609539229,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9451142647196181,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7510122845400926,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8090165300577936,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9543128468386116,
    "sentence_nr": 29
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "en",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "openai/gpt-4o-mini",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.920197561569537,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.1-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8759929746436435,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3-70b-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-small-24b-instruct-2501",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8935424392990651,
    "sentence_nr": 29
  },
  {
    "model": "mistralai/mistral-nemo",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.7769676399488106,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8875472267363329,
    "sentence_nr": 29
  },
  {
    "model": "google/gemini-2.0-flash-lite-001",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "google/gemma-3-27b-it",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "qwen/qwq-32b",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8664932988313133,
    "sentence_nr": 29
  },
  {
    "model": "microsoft/phi-4-multimodal-instruct",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.906379768806771,
    "sentence_nr": 29
  },
  {
    "model": "amazon/nova-micro-v1",
    "bcp_47": "zh",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8001297194719582,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "hi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9048724843551281,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "es",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8947987168857687,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ar",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9489238765618674,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ur",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.945278116491169,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "bn",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pt",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "pa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8989194854163256,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ru",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "sw",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9061728639858796,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "id",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9501419212325259,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "de",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.891206254843651,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ja",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9331628274049639,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "te",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "mr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "jv",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9046319474149982,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "vi",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9463095328863311,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ta",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9085828484030862,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fa",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "tr",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "yue",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.8856061163721227,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "ko",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "it",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "fil",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.9661878700572512,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "arz",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 1.0,
    "sentence_nr": 29
  },
  {
    "model": "meta-llama/llama-3.3-70b-instruct",
    "bcp_47": "gu",
    "task": "language_modeling",
    "metric": "chrf",
    "score": 0.908669313428767,
    "sentence_nr": 29
  }
]