AIME 2024 Leaderboard
Compare models on AIME 2024 benchmarks.
Last updated: May 22, 2025
Rank | Model | Score | Organization | License | Updated At |
---|---|---|---|---|---|
1 | o4-miniOpenAI | 93.4% | OpenAI | Proprietary | May 22, 2025 |
2 | google-gemini-2.5-pro-previewGoogle | 92 | Proprietary | May 18, 2025 | |
3 | o3-2025-04-16OpenAI | 91.6% | OpenAI | Proprietary | May 22, 2025 |
4 | o3OpenAI | 91.6% | OpenAI | Proprietary | May 22, 2025 |
5 | google-gemini-2.5-flash-previewGoogle | 88 | Proprietary | May 18, 2025 | |
6 | gpt-4o-miniOpenAI | 87.3% | OpenAI | Proprietary | May 22, 2025 |
7 | o3-miniOpenAI | 87.3% | OpenAI | Proprietary | May 22, 2025 |
8 | o1OpenAI | 79.2% | OpenAI | Proprietary | May 22, 2025 |
9 | o1-miniOpenAI | 63.6% | OpenAI | Proprietary | May 22, 2025 |
10 | gpt-4.1-miniOpenAI | 49.6% | OpenAI | Proprietary | May 22, 2025 |
11 | gpt-4.1OpenAI | 48.1% | OpenAI | Proprietary | May 22, 2025 |
12 | gpt-4.1-nanoOpenAI | 29.4 | OpenAI | Proprietary | May 22, 2025 |
13 | claude-3-7-sonnet-20250219Anthropic | 23.3% | Anthropic | Proprietary | May 22, 2025 |
14 | claude-3-7-sonnet-latestAnthropic | 23.3% | Anthropic | Proprietary | May 22, 2025 |
15 | anthropic-claude-3-7-sonnetAnthropic | 23.3% | Anthropic | Proprietary | May 22, 2025 |
16 | anthropic-claude-3-5-sonnetAnthropic | 16% | Anthropic | Proprietary | May 22, 2025 |
17 | claude-3-5-sonnet-20241022Anthropic | 16 % | Anthropic | Proprietary | May 22, 2025 |
18 | claude-3-5-sonnet-20240620Anthropic | 16% | Anthropic | Proprietary | May 22, 2025 |
19 | claude-3-5-sonnet-latestAnthropic | 16% | Anthropic | Proprietary | May 22, 2025 |
20 | gpt-4o-2024-05-13OpenAI | 13.4% | OpenAI | Proprietary | May 22, 2025 |
21 | gpt-4o-2024-11-20OpenAI | 13.4% | OpenAI | Proprietary | May 22, 2025 |
22 | chatgpt-4oOpenAI | 13.4% | OpenAI | Proprietary | May 22, 2025 |
23 | gpt-4oOpenAI | 13.4% | OpenAI | Proprietary | May 22, 2025 |
24 | gpt-4o-2024-08-06OpenAI | 13.4% | OpenAI | Proprietary | May 22, 2025 |