| Benchmark | Model | Rank | Results |
|---|---|---|---|
| multi-task-language-understanding-on-mmlu-pro | DATPO (Qwen3-4B-Base) | #102 | Accuracy: 57.7 |
| mathematical-reasoning-on-math-500 | DATPO (Qwen3-4B-Base) | #103 | Accuracy: 76.4 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | DATPO (Qwen3-4B-Base) | #128 | Accuracy: 39.6 |
| mathematical-reasoning-on-aime24 | DATPO (Qwen3-4B-Base) | #129 | Acc: 14.0 |
| mathematical-reasoning-on-aime-2025 | DATPO (Qwen3-4B-Base) | #142 | Accuracy: 10.9 |