AIME 2024: leaderboard
AIME 2024: Measures mathematical reasoning, symbolic problem solving, proof construction, or competition-style problem solving.
Metric: Score (percentage). Source: artofproblemsolving.com. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 4 | 94 | #181 |
| 2 | Magistral Medium 1.2 | 91.8 | #419 |
| 3 | DeepSeek R1 0528 | 91.4 | #222 |
| 4 | Mistral Large 3 | 53.3 | #401 |
| 5 | Reka Flash 3 | 51 | #619 |
| 6 | Median Expert | 33.33 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=aime-2024 · How It Works · Data refreshed daily, snapshot 2026-10-20.