[ { "Model": "llama-3.1-8b", "CR": "57.0", "S-Acc": "16.0", "EM": "0.0", "PM-0.5": "8.0", "Tokens": "1292" }, { "Model": "llama-3.1-70b", "CR": "56.0", "S-Acc": "22.8", "EM": "2.0", "PM-0.5": "18.0", "Tokens": "1164" }, { "Model": "llama-3.3-70b", "CR": "80.5", "S-Acc": "32.2", "EM": "1.0", "PM-0.5": "25.0", "Tokens": "1738" }, { "Model": "mistral-7b", "CR": "97.0", "S-Acc": "19.1", "EM": "0.0", "PM-0.5": "4.5", "Tokens": "1617" }, { "Model": "mistral-small-22b", "CR": "99.5", "S-Acc": "30.7", "EM": "0.5", "PM-0.5": "12.5", "Tokens": "1514" }, { "Model": "mistral-large-123b", "CR": "100.0", "S-Acc": "38.3", "EM": "3.0", "PM-0.5": "30.5", "Tokens": "1636" }, { "Model": "qwen-2.5-7b", "CR": "96.5", "S-Acc": "25.8", "EM": "0.0", "PM-0.5": "8.5", "Tokens": "1395" }, { "Model": "qwen-2.5-32b", "CR": "93.0", "S-Acc": "32.2", "EM": "0.0", "PM-0.5": "22.5", "Tokens": "1207" }, { "Model": "qwen-2.5-72b", "CR": "93.5", "S-Acc": "34.0", "EM": "0.0", "PM-0.5": "23.0", "Tokens": "1809" }, { "Model": "qwq-32b", "CR": "78.5", "S-Acc": "46.3", "EM": "19.5", "PM-0.5": "48.0", "Tokens": "9523" }, { "Model": "deepseek-R1", "CR": "100.0", "S-Acc": "69.4", "EM": "42.5", "PM-0.5": "68.0", "Tokens": "9204" }, { "Model": "gemini-2.0-exp", "CR": "58.0", "S-Acc": "24.2", "EM": "2.0", "PM-0.5": "20.0", "Tokens": "2103" }, { "Model": "gemini-2.0-thinking", "CR": "99.0", "S-Acc": "45.9", "EM": "8.0", "PM-0.5": "37.5", "Tokens": "4037" }, { "Model": "openai-gpt-4o", "CR": "100.0", "S-Acc": "39.3", "EM": "3.5", "PM-0.5": "29.5", "Tokens": "953" }, { "Model": "openai-o1-mini", "CR": "99.0", "S-Acc": "57.2", "EM": "23.5", "PM-0.5": "53.5", "Tokens": "10242" }, { "Model": "openai-o1-preview", "CR": "99.0", "S-Acc": "68.8", "EM": "41.0", "PM-0.5": "68.5", "Tokens": "9449" } ]