| Benchmark | Model | Rank | Results |
|---|---|---|---|
| vision-language-understanding-on-mmstar | ReaGEN (Qwen3-VL-4B, 4 iter) | #2 | Accuracy: 84.49 |
| mathematical-reasoning-on-mathverse | ReaGEN (Qwen3-VL-4B, 4 iter) | #19 | Accuracy: 47.59 |
| multimodal-reasoning-on-mathvision | ReaGEN (Qwen3-VL-4B, 4 iter) | #34 | Accuracy: 44.6 |