| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-olympiadbench | DeepSeek-R1-Distill-Qwen-1.5B + GAPO | #19 | Accuracy: 59.4 |
| mathematical-reasoning-on-math-500 | DeepSeek-R1-Distill-Qwen-1.5B + GAPO | #69 | Accuracy: 85.5 |
| mathematical-reasoning-on-aime24 | DeepSeek-R1-Distill-Qwen-1.5B + GAPO | #89 | Acc: 44 |
| mathematical-reasoning-on-aime-2025 | DeepSeek-R1-Distill-Qwen-1.5B + GAPO | #111 | Accuracy: 30.8 |