| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2025 | Qwen3-30B-A3B-Thinking + ACC | – | Accuracy: 90.0 |
| mathematical-reasoning-on-aime24 | Qwen3-30B-A3B-Thinking + ACC | – | Acc: 90.0 |
| multi-task-language-understanding-on-mmlu-pro | Qwen3-30B-A3B-Thinking + ACC | – | Accuracy: 76.0 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Qwen3-30B-A3B-Thinking + ACC | – | Accuracy: 70.2 |