| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2025 | Qwen3-30B-A3B (fine-tuned on Nemotron-Math AoPS+StackExchange-Math subset, high reasoning, Python TIR) | #3 | Accuracy: 97.29 |
| mathematical-reasoning-on-aime24 | Qwen3-30B-A3B (fine-tuned on Nemotron-Math, high reasoning, Python TIR, full-data training) | #3 | Acc: 94.67 |