| Benchmark | Model | Rank | Results |
|---|---|---|---|
| code-generation-on-mbpp | CopT (Qwen3-8B) | #4 | Accuracy: 94.55 |
| code-generation-on-humaneval | CopT (Qwen3-8B) | #9 | Pass@1: 96.34 |
| mathematical-reasoning-on-math-500 | CopT (Qwen3-8B) | #9 | Accuracy: 97.6 |
| arithmetic-reasoning-on-gsm8k | CopT (Qwen3-8B) | #10 | Accuracy: 96.36 |
| mathematical-reasoning-on-aime24 | CopT (Qwen3-8B) | #37 | Acc: 79.17 |
| mathematical-reasoning-on-aime-2025 | CopT (Qwen3-8B) | #55 | Accuracy: 70.42 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | CopT (Qwen3-8B) | #94 | Accuracy: 61.62 |