ai-progress-charts / zeroeval_math_l5_leaderboard.jsonl
kaizuberbuehler's picture
Add new benchmarks; Several improvements
afb8d0c
{"model": "o1-preview-2024-09-12", "score": 84.5}
{"model": "o1-mini-2024-09-12", "score": 89.3}
{"model": "claude-3-5-sonnet-20241022", "score": 59.4}
{"model": "gemini-1.5-pro-exp-0827", "score": 68.1}
{"model": "gpt-4o-2024-08-06", "score": 55.3}
{"model": "chatgpt-4o-latest-24-09-07", "score": 53.1}
{"model": "gpt-4o-2024-05-13", "score": 54.8}
{"model": "claude-3-5-sonnet-20240620", "score": 51.9}
{"model": "grok-2-1212", "score": 60.9}
{"model": "qwen2.5-72b-instruct", "score": 60.2}
{"model": "llama-3.1-405b-instruct", "score": 49.8}
{"model": "gpt-4-turbo-2024-04-09", "score": 46.5}
{"model": "gemini-1.5-flash-exp-0827", "score": 54.5}
{"model": "mistral-large-2", "score": 48.5}
{"model": "gpt-4o-mini-2024-07-18", "score": 52.2}
{"model": "deepseek-v2.5-0908", "score": 44.7}
{"model": "claude-3-opus-20240229", "score": 36.9}
{"model": "meta-llama-3.1-70b-instruct", "score": 43.1}
{"model": "claude-3-5-haiku-20241022", "score": 46.5}
{"model": "gemini-1.5-pro", "score": 39.8}
{"model": "gpt-4-0314", "score": 26.1}