| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2025 | CoPD | – | Accuracy: 49.58 |
| mathematical-reasoning-on-aime24 | CoPD | – | Acc: 60.42 |
| mathematical-reasoning-on-math-500 | CoPD | – | Accuracy: 94.5 |
| multimodal-reasoning-on-mathvision | CoPD | – | Accuracy: 57.88 |
| multimodal-reasoning-on-mathvista | CoPD | – | Accuracy: 76.8 |
| multimodal-reasoning-on-mmmu | CoPD | – | Accuracy: 67.78 |
| multimodal-reasoning-on-mmmu-pro | CoPD | – | Accuracy: 55.12 |