Spaces:
Running
Running
Model Name,logics,coding,technology,history,science,general culture,creative writing,grammar,current news,math,General Average | |
claude-3.5-haiku-20241022,3.85,4,4.07,4.15,4.05,4.11,4.2,3.98,4.04,3.44,3.99 | |
claude-3.7-sonnet,3.96,4.27,4.3,4.34,4.29,4.31,4.41,4.14,4.15,3.87,4.2 | |
claude-3.7-sonnet:thinking,4.18,4.48,4.48,4.54,4.45,4.48,4.48,4.4,4.32,4.06,4.39 | |
deepSeek-R1,3.97,4.05,4.39,4.39,4.35,4.35,4.46,4.32,4.29,3.95,4.26 | |
deepSeek-V3,4.04,4.01,4.12,4.06,4.13,4.14,4.32,4.11,4.08,3.91,4.09 | |
deepSeek-V3-0324,4.07,4.25,4.13,4.18,4.11,4.17,4.33,4.22,4.17,3.97,4.16 | |
gemini-2.0-flash-001,3.97,4.18,4.29,4.3,4.25,4.28,3.99,4.24,4.18,3.85,4.16 | |
gemini-2.5-pro-preview-03-25,4.17,4.5,4.59,4.6,4.56,4.59,4.42,4.53,4.48,4.17,4.46 | |
gemma-3-27b-it,3.9,3.98,4.34,4.38,4.33,4.36,4.35,4.33,4.29,3.7,4.2 | |
gpt-4.1-mini,4.3,4.42,4.4,4.32,4.3,4.3,4.41,4.44,4.22,4.34,4.34 | |
gpt-4o-mini,3.82,3.97,4.07,4.03,4.07,4.1,4.2,3.97,4,3.79,4 | |
grok-2-1212,3.92,4.12,4.14,4.16,4.19,4.17,4.17,4.16,4.08,3.87,4.1 | |
grok-3-beta,4.05,4.33,4.36,4.45,4.42,4.43,4.47,4.54,4.36,4.07,4.34 | |
llama-3.1-Nemotron-70B-Instruct-HF,3.99,4.1,4.29,4.32,4.3,4.32,4.3,4.27,4.2,3.68,4.18 | |
llama-3.3-70B-Instruct,3.93,3.83,4.21,4.13,4.15,4.17,4.02,4.1,4.07,3.52,4.02 | |
llama-3_1-Nemotron-Ultra-253B-v1,4.06,4.17,4.36,4.34,4.31,4.33,4.38,4.36,4.33,3.91,4.26 | |
llama-4-Maverick-17B-128E-Instruct-FP8,3.86,3.98,4.1,4.1,4.1,4.05,4.04,4.1,3.99,3.64,4 | |
llama-4-Scout-17B-16E-Instruct,3.89,3.88,4.09,4.11,4.14,4.1,4.04,4.09,4.04,3.53,4 | |
mistral-large-2411,3.87,3.98,4.18,4.09,4.17,4.08,4.19,4.05,4.07,3.88,4.05 | |
mistral-small-24b-instruct-2501,3.66,3.86,4.08,4.02,4.09,4.05,3.42,3.94,4.01,3.59,3.88 | |
nova-lite-v1,3.77,3.73,4.05,4.02,4.02,4.04,3.86,3.9,3.86,3.56,3.89 | |
nova-pro-v1,3.74,3.81,3.86,3.82,3.86,3.9,4.06,3.91,3.78,3.56,3.83 | |
o3-mini-2025-01-31,4.32,4.44,4.25,4.21,4.21,4.2,4.35,4.23,4.09,4.41,4.26 | |
o4-mini-2025-04-16,4.48,4.55,4.61,4.61,4.67,4.59,4.51,4.6,4.57,4.57,4.57 | |
qwen-plus,4.1,4.23,4.24,4.21,4.22,4.17,4.3,4.19,4.06,4.03,4.17 | |