| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-olympiadbench | LEAD (DeepSeek-R1-Distill-Qwen-7B) | #14 | Accuracy: 65.14 |
| mathematical-reasoning-on-math-500 | LEAD (DeepSeek-R1-Distill-Qwen-7B) | #48 | Accuracy: 92.27 |
| mathematical-reasoning-on-aime24 | LEAD (DeepSeek-R1-Distill-Qwen-7B) | #88 | Acc: 44.67 |
| mathematical-reasoning-on-aime-2025 | LEAD (DeepSeek-R1-Distill-Qwen-7B) | #108 | Accuracy: 35.0 |