| Benchmark | Model | Rank | Results |
|---|---|---|---|
| arithmetic-reasoning-on-gsm8k | DiagEvo (Qwen3-8B, 235B-A22B diagnostician) | – | Accuracy: 94.1 |
| mathematical-reasoning-on-minerva-math | DiagEvo (Qwen3-8B, 235B-A22B diagnostician) | – | Accuracy: 64.8 |
| mathematical-reasoning-on-olympiadbench | DiagEvo (Qwen3-8B, 235B-A22B diagnostician) | – | Accuracy: 53.8 |
| multi-task-language-understanding-on-mmlu-pro | DiagEvo (Qwen3-8B, 235B-A22B diagnostician) | – | Accuracy: 63.1 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | DiagEvo (Qwen3-8B, 235B-A22B diagnostician) | – | Accuracy: 47.5 |