{"model": "o3-mini-2025-01-31-high", "score": 77.29} {"model": "o1-2024-12-17-high", "score": 80.32} {"model": "deepseek-r1", "score": 80.71} {"model": "o3-mini-2025-01-31-medium", "score": 72.37} {"model": "gemini-2.0-flash-thinking-exp-01-21", "score": 75.85} {"model": "gemini-2.0-pro-exp-02-05", "score": 70.97} {"model": "gemini-exp-1206", "score": 72.36} {"model": "o3-mini-2025-01-31-low", "score": 63.06} {"model": "qwen2.5-max", "score": 58.35} {"model": "gemini-2.0-flash", "score": 65.62} {"model": "deepseek-v3", "score": 60.54} {"model": "gemini-2.0-flash-exp", "score": 60.39} {"model": "claude-3-5-sonnet-20241022", "score": 52.28} {"model": "chatgpt-4o-latest-2025-01-29", "score": 48.02} {"model": "o1-mini-2024-09-12", "score": 61.99} {"model": "step-2-16k-202411", "score": 48.77} {"model": "gpt-4o-2024-08-06", "score": 49.54} {"model": "gemini-1.5-pro-002", "score": 59.07} {"model": "grok-2-1212", "score": 54.88} {"model": "gemini-2.0-flash-lite-preview-02-05", "score": 55.54} {"model": "dracarys2-72b-instruct", "score": 54.66} {"model": "meta-llama-3.1-405b-instruct-turbo", "score": 41.07} {"model": "gpt-4o-2024-11-20", "score": 42.87} {"model": "learnlm-1.5-pro-experimental", "score": 57.75} {"model": "chatgpt-4o-latest-0903", "score": 42.45} {"model": "qwen2.5-72b-instruct-turbo", "score": 54.29} {"model": "gpt-4-turbo-2024-04-09", "score": 43.02} {"model": "llama-3.3-70b-instruct-turbo", "score": 42.24} {"model": "deepseek-r1-distill-llama-70b", "score": 58.11} {"model": "grok-beta", "score": 45.84} {"model": "claude-3-opus-20240229", "score": 43.62} {"model": "mistral-large-2411", "score": 42.55} {"model": "qwen2.5-coder-32b-instruct", "score": 46.61} {"model": "dracarys2-llama-3.1-70b-instruct", "score": 40.30} {"model": "meta-llama-3.1-70b-instruct-turbo", "score": 34.72} {"model": "amazon.nova-pro-v1:0", "score": 38.04} {"model": "claude-3-5-haiku-20241022", "score": 35.54} {"model": "deepseek-r1-distill-qwen-32b", "score": 59.36} {"model": "mistral-small-2501", "score": 39.89} {"model": "phi-4", "score": 41.98} {"model": "gpt-4o-mini-2024-07-18", "score": 36.31} {"model": "qwq-32b-preview", "score": 58.26} {"model": "gemma-2-27b-it", "score": 26.46} {"model": "amazon.nova-lite-v1:0", "score": 36.70} {"model": "qwen2.5-7b-instruct-turbo", "score": 39.51} {"model": "mistral-small-2409", "score": 24.42} {"model": "command-r-plus-08-2024", "score": 21.27} {"model": "amazon.nova-micro-v1:0", "score": 34.49} {"model": "gemma-2-9b-it", "score": 19.80} {"model": "command-r-08-2024", "score": 19.39} {"model": "command-r-plus-04-2024", "score": 17.99} {"model": "meta-llama-3.1-8b-instruct-turbo", "score": 18.31} {"model": "phi-3-small-8k-instruct", "score": 17.58} {"model": "phi-3-mini-128k-instruct", "score": 15.72} {"model": "olmo-2-1124-13b-instruct", "score": 13.64} {"model": "phi-3-mini-4k-instruct", "score": 14.96}