OpenEvals - AIME 2026: leaderboard
Hugging Face OpenEvals official leaderboard covering AIME 2026 competition math problems.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Step 3.5 Flash | 96.67 | #270 |
| 2 | Kimi K2.5 | 95.83 | #144 |
| 3 | GLM-5 | 95.83 | #141 |
| 4 | DeepSeek V3.2 | 94.17 | #205 |
| 5 | Qwen 3.5 397B A17B | 93.33 | #146 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openevals-aime-2026 · How It Works · Data refreshed daily, snapshot 2026-10-20.