| Benchmark | Model | Rank | Results |
|---|---|---|---|
| code-generation-on-humaneval | OSCAR (GLM-4.7, 358B) | #27 | Pass@1: 91.06 |
| mathematical-reasoning-on-math-500 | OSCAR (GLM-4.7, 358B) | #33 | Accuracy: 94.66 |
| mathematical-reasoning-on-aime-2025 | OSCAR (GLM-4.7, 358B) | #43 | Accuracy: 78.89 |
| code-generation-on-livecodebench-v6 | OSCAR (GLM-4.7, 358B) | #49 | Pass@1: 52.63 |