| Benchmark | Model | Rank | Results |
|---|---|---|---|
| arithmetic-reasoning-on-gsm8k | APPO (Qwen2.5-7B-Instruct) | #41 | Accuracy: 93.2 |
| mathematical-reasoning-on-math-500 | APPO (Qwen2.5-7B-Instruct) | #89 | Accuracy: 81.0 |
| mathematical-reasoning-on-aime-2025 | APPO (Qwen2.5-7B-Instruct) | #112 | Accuracy: 30.0 |