| Benchmark | Model | Rank | Results |
|---|---|---|---|
| code-generation-on-humaneval | Edge0-8B | #26 | Pass@1: 91.5 |
| mathematical-reasoning-on-aime-2026 | Edge0-35B-A3B-preview | #27 | Accuracy: 86.6 |
| multi-task-language-understanding-on-mmlu-pro | Edge0-35B-A3B-preview | #40 | Accuracy: 81.0 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Edge0-35B-A3B-preview | #56 | Accuracy: 79.8 |