| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime24 | Qwen3-30B-A3B-Instruct (LUSPO) | #21 | Acc: 83.6 |
| multimodal-reasoning-on-mathvista | Qwen2.5-VL-7B-Instruct (LUSPO) | #49 | Accuracy: 74.4 |
| multimodal-reasoning-on-mathvision | Qwen2.5-VL-7B-Instruct (LUSPO) | #52 | Accuracy: 28.0 |
| mathematical-reasoning-on-math-500 | Qwen2.5-7B-Base (LUSPO) | #97 | Accuracy: 78.4 |