Add Humanity's Last Exam, LiveBench and LiveCodeBench; Remove Codeforces; Update Simple Bench
b605a32
{"model": "o3-mini-2025-01-31-high", "score": 75.88} | |
{"model": "o1-2024-12-17-high", "score": 75.67} | |
{"model": "deepseek-r1", "score": 71.57} | |
{"model": "o3-mini-2025-01-31-medium", "score": 70.01} | |
{"model": "gemini-2.0-flash-thinking-exp-01-21", "score": 66.92} | |
{"model": "gemini-2.0-pro-exp-02-05", "score": 65.13} | |
{"model": "gemini-exp-1206", "score": 64.09} | |
{"model": "o3-mini-2025-01-31-low", "score": 62.45} | |
{"model": "qwen2.5-max", "score": 62.29} | |
{"model": "gemini-2.0-flash", "score": 61.47} | |
{"model": "deepseek-v3", "score": 60.45} | |
{"model": "gemini-2.0-flash-exp", "score": 59.26} | |
{"model": "claude-3-5-sonnet-20241022", "score": 59.03} | |
{"model": "chatgpt-4o-latest-2025-01-29", "score": 57.79} | |
{"model": "o1-mini-2024-09-12", "score": 57.76} | |
{"model": "step-2-16k-202411", "score": 56.02} | |
{"model": "gpt-4o-2024-08-06", "score": 55.33} | |
{"model": "gemini-1.5-pro-002", "score": 54.33} | |
{"model": "grok-2-1212", "score": 54.30} | |
{"model": "gemini-2.0-flash-lite-preview-02-05", "score": 53.24} | |
{"model": "dracarys2-72b-instruct", "score": 52.64} | |
{"model": "meta-llama-3.1-405b-instruct-turbo", "score": 52.36} | |
{"model": "gpt-4o-2024-11-20", "score": 52.19} | |
{"model": "learnlm-1.5-pro-experimental", "score": 52.19} | |
{"model": "chatgpt-4o-latest-0903", "score": 51.66} | |
{"model": "qwen2.5-72b-instruct-turbo", "score": 51.44} | |
{"model": "gpt-4-turbo-2024-04-09", "score": 50.40} | |
{"model": "llama-3.3-70b-instruct-turbo", "score": 50.16} | |
{"model": "deepseek-r1-distill-llama-70b", "score": 49.66} | |
{"model": "grok-beta", "score": 49.18} | |
{"model": "claude-3-opus-20240229", "score": 49.16} | |
{"model": "mistral-large-2411", "score": 48.43} | |
{"model": "qwen2.5-coder-32b-instruct", "score": 46.23} | |
{"model": "dracarys2-llama-3.1-70b-instruct", "score": 46.21} | |
{"model": "meta-llama-3.1-70b-instruct-turbo", "score": 44.89} | |
{"model": "amazon.nova-pro-v1:0", "score": 43.53} | |
{"model": "claude-3-5-haiku-20241022", "score": 43.45} | |
{"model": "deepseek-r1-distill-qwen-32b", "score": 42.93} | |
{"model": "mistral-small-2501", "score": 42.55} | |
{"model": "phi-4", "score": 41.61} | |
{"model": "gpt-4o-mini-2024-07-18", "score": 41.26} | |
{"model": "qwq-32b-preview", "score": 40.25} | |
{"model": "gemma-2-27b-it", "score": 38.18} | |
{"model": "amazon.nova-lite-v1:0", "score": 36.35} | |
{"model": "qwen2.5-7b-instruct-turbo", "score": 34.90} | |
{"model": "mistral-small-2409", "score": 33.42} | |
{"model": "command-r-plus-08-2024", "score": 31.76} | |
{"model": "amazon.nova-micro-v1:0", "score": 29.59} | |
{"model": "gemma-2-9b-it", "score": 28.66} | |
{"model": "command-r-08-2024", "score": 27.48} | |
{"model": "command-r-plus-04-2024", "score": 27.11} | |
{"model": "meta-llama-3.1-8b-instruct-turbo", "score": 25.97} | |
{"model": "phi-3-small-8k-instruct", "score": 24.03} | |
{"model": "phi-3-mini-128k-instruct", "score": 22.36} | |
{"model": "olmo-2-1124-13b-instruct", "score": 22.12} | |
{"model": "phi-3-mini-4k-instruct", "score": 22.08} |