| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2025 | Qwen3.5-35B-A3B + VP | – | Accuracy: 90.21 |
| multimodal-reasoning-on-mathvista | Qwen3.5-35B-A3B + VP | – | Accuracy: 86.70 |
| multimodal-reasoning-on-mmmu-pro | Qwen3.5-35B-A3B + VP | – | Accuracy: 73.87 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Qwen3.5-35B-A3B + VP | – | Accuracy: 79.29 |
| question-answering-on-humanity-s-last-exam-hle | Qwen3.5-35B-A3B + VP | – | Accuracy: 16.67 |