Math 500 Leaderboard
Compare models on Math 500 benchmarks.
Rank | Model | Score | Organization | License |
---|---|---|---|---|
1 | GPT-4o miniOpenAI | 97.9% | OpenAI | Proprietary |
2 | o3-miniOpenAI | 97.9% | OpenAI | Proprietary |
3 | o1OpenAI | 96.4% | OpenAI | Proprietary |
4 | o1-miniOpenAI | 90% | OpenAI | Proprietary |
5 | Gemini 2.0 FlashGoogle | 89.7 | Proprietary | |
6 | Gemini 2.0 FlashGoogle | 89.7% | Proprietary | |
7 | Claude 3.7 SonnetAnthropic | 82.2% | Anthropic | Proprietary |
8 | Claude 3.5 SonnetAnthropic | 78% | Anthropic | Proprietary |
9 | Claude 3.5 HaikuAnthropic | 69.4% | Anthropic | Proprietary |
10 | Claude 3 HaikuAnthropic | 69.4% | Anthropic | Proprietary |
11 | GPT-4oOpenAI | 60.3% | OpenAI | Proprietary |
12 | GPT-4oOpenAI | 60.3% | OpenAI | Proprietary |
13 | ChatGPT-4oOpenAI | 60.3% | OpenAI | Proprietary |
14 | GPT-4oOpenAI | 60.3% | OpenAI | Proprietary |
15 | GPT-4oOpenAI | 60.3% | OpenAI | Proprietary |