[ { "Model": "llama-3.1-8b", "CR": "43.0", "S-Acc": "5.5", "EM": "0.0", "PM-0.5": "0.0", "Tokens": "3712" }, { "Model": "llama-3.1-70b", "CR": "84.0", "S-Acc": "35.8", "EM": "0.0", "PM-0.5": "21.0", "Tokens": "3565" }, { "Model": "llama-3.3-70b", "CR": "97.0", "S-Acc": "40.8", "EM": "0.0", "PM-0.5": "28.0", "Tokens": "3584" }, { "Model": "mistral-7b", "CR": "75.0", "S-Acc": "7.9", "EM": "0.0", "PM-0.5": "0.0", "Tokens": "4599" }, { "Model": "mistral-small-22b", "CR": "67.0", "S-Acc": "5.5", "EM": "0.0", "PM-0.5": "0.0", "Tokens": "4170" }, { "Model": "mistral-large-123b", "CR": "98.0", "S-Acc": "39.4", "EM": "0.0", "PM-0.5": "20.0", "Tokens": "4279" }, { "Model": "qwen-2.5-7b", "CR": "42.0", "S-Acc": "3.6", "EM": "0.0", "PM-0.5": "0.0", "Tokens": "4159" }, { "Model": "qwen-2.5-32b", "CR": "100.0", "S-Acc": "31.8", "EM": "0.0", "PM-0.5": "2.0", "Tokens": "4073" }, { "Model": "qwen-2.5-72b", "CR": "100.0", "S-Acc": "39.3", "EM": "0.0", "PM-0.5": "18.0", "Tokens": "4110" }, { "Model": "qwq-32b", "CR": "97.0", "S-Acc": "31.6", "EM": "0.0", "PM-0.5": "6.0", "Tokens": "4964" }, { "Model": "deepseek-R1", "CR": "100.0", "S-Acc": "62.2", "EM": "0.0", "PM-0.5": "83.0", "Tokens": "10076" }, { "Model": "gemini-2.0-exp", "CR": "98.0", "S-Acc": "48.0", "EM": "0.0", "PM-0.5": "48.0", "Tokens": "4019" }, { "Model": "gemini-2.0-thinking", "CR": "92.0", "S-Acc": "40.7", "EM": "0.0", "PM-0.5": "27.0", "Tokens": "4256" }, { "Model": "openai-gpt-4o", "CR": "100.0", "S-Acc": "56.0", "EM": "0.0", "PM-0.5": "67.0", "Tokens": "3229" }, { "Model": "openai-o1-mini", "CR": "97.0", "S-Acc": "34.7", "EM": "0.0", "PM-0.5": "12.0", "Tokens": "10951" }, { "Model": "openai-o1-preview", "CR": "100.0", "S-Acc": "67.2", "EM": "0.0", "PM-0.5": "90.0", "Tokens": "14847" } ]