| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-mathverse | CPPO (Qwen2.5-VL-7B) | #21 | Accuracy: 46.5 |
| multimodal-reasoning-on-mathvision | CPPO (Qwen2.5-VL-7B) | #50 | Accuracy: 29.9 |
| multimodal-reasoning-on-mathvista | CPPO (Qwen2.5-VL-7B) | #57 | Accuracy: 72.2 |