# AIME 2024 — AI model rankings

single-answer accuracy on the 2024 invitational mathematics exam without tools

9 tracked models have a published AIME 2024 score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | gpt-oss-120b | OpenAI | 95.8% | Lab | Aug 5 2025 |
| 2 | gpt-oss-20b | OpenAI | 92.1% | Lab | Aug 5 2025 |
| 3 | Gemini 2.5 Pro | Google | 92% | Lab | Mar 25 2025 |
| 4 | o1-mini | OpenAI | 70% | Lab | Sep 12 2024 |
| 5 | GPT-4.1 mini | OpenAI | 49.6% | Lab | Apr 14 2025 |
| 6 | GPT-4.1 | OpenAI | 48.1% | Lab | Apr 14 2025 |
| 7 | o1-preview | OpenAI | 44.6% | Lab | Sep 12 2024 |
| 8 | GPT-4.5 | OpenAI | 36.7% | Lab | Feb 27 2025 |
| 9 | GPT-4.1 nano | OpenAI | 29.4% | Lab | Apr 14 2025 |


---

Canonical page: https://aireleasetracker.com/benchmark/aime-2024
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.