Physical Reasoning on PHYBench
5.3Pass@1 AccuracyAERO
Evaluation Results
| Method | Links | |
|---|---|---|
| AEROBackbone Model=Qwen3-8B-Base, Evolutionary Round=R52026.02 | 5.3 | |
| AEROBackbone Model=Qwen3-8B-Base, Evolutionary Round=R42026.02 | 5.1 | |
| AEROBackbone Model=Qwen3-8B-Base, Evolutionary Round=R32026.02 | 4 | |
| AEROBackbone Model=Qwen3-4B-Base, Evolutionary Round=R52026.02 | 3.9 | |
| Qwen3-8B-BaseBackbone Model=Qwen3-8B-Base2026.02 | 3.8 | |
| AEROBackbone Model=Qwen3-8B-Base, Evolutionary Round=R22026.02 | 3.8 | |
| AEROBackbone Model=Qwen3-4B-Base, Evolutionary Round=R42026.02 | 3.7 | |
| AEROBackbone Model=Qwen3-4B-Base, Evolutionary Round=R32026.02 | 3.4 | |
| AEROBackbone Model=Qwen3-8B-Base, Evolutionary Round=R12026.02 | 3.4 | |
| Qwen3-4B-BaseBackbone Model=Qwen3-4B-Base2026.02 | 2.7 | |
| AEROBackbone Model=Qwen3-4B-Base, Evolutionary Round=R12026.02 | 2.7 | |
| AEROBackbone Model=Qwen3-4B-Base, Evolutionary Round=R22026.02 | 2.7 |