| Benchmark | Model | Rank | Results |
|---|---|---|---|
| code-generation-on-mbpp | SCOUT | – | Accuracy: 65.2 |
| mathematical-reasoning-on-aime-2025 | SCOUT | – | Accuracy: 31.2 |
| mathematical-reasoning-on-aime24 | SCOUT | – | Acc: 39.8 |
| mathematical-reasoning-on-math-500 | SCOUT | – | Accuracy: 90.0 |
| mathematical-reasoning-on-olympiadbench | SCOUT | – | Accuracy: 62.4 |