Mathematical Proof on IMO 2025
88.69ScoreSTAR-PólyaMath
Evaluation Results
| Method | Links | |
|---|---|---|
| STAR-PólyaMathBackbone=all GPT-5.5xh2026.05 | 88.69 | |
| GPT-5.4Reasoning Effort=xhigh2026.05 | 78.57 | |
| GPT-5.5Reasoning Effort=xhigh2026.05 | 70.83 | |
| Claude Opus 4.7Reasoning Effort=xhigh2026.05 | 70.24 | |
| Gemini 3.1 Pro2026.05 | 67.26 | |
| GPT-5.2Reasoning Effort=high2026.05 | 58.33 | |
| Gemini 3 Pro2026.05 | 41.67 | |
| Claude Opus 4.6Reasoning Effort=high2026.05 | 30.36 |