USAMO 2026
Math · 2026-03-28
2026 USAMO proof-grading benchmark at med/high/xhigh effort.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Mythos 5 | 99.8 |
| GPT-5.5 | 98.2 |
| Claude Mythos Preview | 97.6 |
| Opus 4.8 | 96.7 |
| GPT-5.4 | 95.2 |
| Sonnet 5 | 79.5 |
| Gemini 3.1 Pro Preview | 74.4 |
| Opus 4.7 | 69.3 |
| DeepSeek-V4-Pro | 60.7 |
| Kimi K2.6 | 51.2 |
| Opus 4.6 | 47.0 |
| Step 3.5 Flash | 44.6 |
| Qwen3.5 397B A17B | 36.3 |
| GLM-5 | 35.1 |