| Benchmark | Model | Rank | Results |
|---|---|---|---|
| code-generation-on-humaneval | IMH (WeDLM-8B) | – | Pass@1: 74.5 |
| code-generation-on-mbpp | IMH (WeDLM-8B) | – | Accuracy: 77.6 |
| mathematical-reasoning-on-aime-2025 | WeDLM-8B (IMH) | – | Accuracy: 7.4000 |
| mathematical-reasoning-on-aime24 | WeDLM-8B (IMH) | – | Acc: 9.5 |
| mathematical-reasoning-on-math-500 | WeDLM-8B (IMH) | – | Accuracy: 54.0 |