[ { "Model": "llama-3.1-8b", "CR": "43.0", "S-Acc": "2.3", "EM": "0.0", "PM-0.5": "0.0", "Tokens": "2067" }, { "Model": "llama-3.1-70b", "CR": "62.0", "S-Acc": "6.9", "EM": "0.0", "PM-0.5": "1.0", "Tokens": "1297" }, { "Model": "llama-3.3-70b", "CR": "99.0", "S-Acc": "14.3", "EM": "0.0", "PM-0.5": "1.0", "Tokens": "1137" }, { "Model": "mistral-7b", "CR": "99.0", "S-Acc": "4.3", "EM": "0.0", "PM-0.5": "0.0", "Tokens": "1095" }, { "Model": "mistral-small-22b", "CR": "95.0", "S-Acc": "7.0", "EM": "0.0", "PM-0.5": "0.0", "Tokens": "1233" }, { "Model": "mistral-large-123b", "CR": "96.0", "S-Acc": "13.7", "EM": "0.0", "PM-0.5": "1.0", "Tokens": "1204" }, { "Model": "qwen-2.5-7b", "CR": "81.0", "S-Acc": "3.5", "EM": "0.0", "PM-0.5": "0.0", "Tokens": "1181" }, { "Model": "qwen-2.5-32b", "CR": "89.0", "S-Acc": "9.8", "EM": "0.0", "PM-0.5": "0.0", "Tokens": "1303" }, { "Model": "qwen-2.5-72b", "CR": "85.0", "S-Acc": "11.8", "EM": "0.0", "PM-0.5": "0.0", "Tokens": "1726" }, { "Model": "qwq-32b", "CR": "47.0", "S-Acc": "3.6", "EM": "0.0", "PM-0.5": "0.0", "Tokens": "6491" }, { "Model": "deepseek-R1", "CR": "100.0", "S-Acc": "26.0", "EM": "4.0", "PM-0.5": "21.0", "Tokens": "10344" }, { "Model": "gemini-2.0-exp", "CR": "47.0", "S-Acc": "8.5", "EM": "0.0", "PM-0.5": "1.0", "Tokens": "1585" }, { "Model": "gemini-2.0-thinking", "CR": "68.0", "S-Acc": "11.2", "EM": "0.0", "PM-0.5": "2.0", "Tokens": "4167" }, { "Model": "openai-gpt-4o", "CR": "100.0", "S-Acc": "20.7", "EM": "0.0", "PM-0.5": "5.0", "Tokens": "739" }, { "Model": "openai-o1-mini", "CR": "100.0", "S-Acc": "22.7", "EM": "1.0", "PM-0.5": "13.0", "Tokens": "11208" }, { "Model": "openai-o1-preview", "CR": "92.0", "S-Acc": "34.8", "EM": "13.0", "PM-0.5": "29.0", "Tokens": "12567" } ]