| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2025 | A2D (Qwen2.5-7B-Instruct) | – | Accuracy: 17.1 |
| mathematical-reasoning-on-aime24 | A2D (Qwen2.5-7B-Instruct) | – | Acc: 20.0 |
| mathematical-reasoning-on-minerva-math | A2D (Qwen2.5-7B-Instruct) | – | Accuracy: 28.9 |