| Benchmark | Model | Rank | Results |
|---|---|---|---|
| arithmetic-reasoning-on-gsm8k | Llama-3.1-8B-Instruct + 35K QwQ-Mole-Syn + RL | – | Accuracy: 90.3 |
| mathematical-reasoning-on-aime-2025 | Llama-3.1-8B-Instruct + Mole-Syn-by-Qwen-32B | – | Accuracy: 8.33 |
| mathematical-reasoning-on-aime24 | Llama-3.1-8B-Instruct + 35K QwQ-Mole-Syn + RL | – | Acc: 10.0 |
| mathematical-reasoning-on-math-500 | Qwen-2.5-7B-Instruct + 20K OSS-Mole-Syn | – | Accuracy: 77.8 |
| mathematical-reasoning-on-olympiadbench | Qwen-2.5-7B-Instruct + 20K OSS-Mole-Syn | – | Accuracy: 37.48 |