| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2025 | Qwen3-4B-Thinking-2507 (4B) fine-tuned on Chimera (SFT+RL) | – | Accuracy: 80.7 |
| mathematical-reasoning-on-aime24 | Qwen3-4B-Thinking-2507 (4B) fine-tuned on Chimera (SFT+RL) | – | Acc: 86.9 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Qwen3-4B-Thinking-2507 (4B) fine-tuned on Chimera (SFT+RL) | – | Accuracy: 70.1 |
| question-answering-on-humanity-s-last-exam-hle | Qwen3-4B-Thinking-2507 (4B) fine-tuned on Chimera (SFT+RL) | – | Accuracy: 9.0 |