Mathematical Proof on USAMO 2026
99.4Overall Score (%)STAR-PólyaMath
Evaluation Results
| Method | Links | |
|---|---|---|
| STAR-PólyaMathBackbone=all GPT-5.5xh2026.05 | 99.4 | |
| GPT-5.5Reasoning Effort=xhigh2026.05 | 98.21 | |
| GPT-5.4Reasoning Effort=xhigh2026.05 | 95.24 | |
| Gemini 3.1 Pro2026.05 | 74.4 | |
| Claude Opus 4.7Reasoning Effort=xhigh2026.05 | 63.1 | |
| DeepSeek-v4-ProReasoning Effort=Max2026.05 | 60.71 | |
| Kimi K2.6Reasoning Effort=Think2026.05 | 51.19 | |
| GPT-5.2Reasoning Effort=high2026.05 | 50 | |
| Claude Opus 4.6Reasoning Effort=high2026.05 | 47.02 |