Scientific Reasoning on Physics (Accuracy)
81.6AccuracySC-SDPO
Evaluation Results
| Method | Links | |
|---|---|---|
| SC-SDPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Cited from prior work2026.06 | 81.6 | |
| DistILBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Cited from prior work2026.06 | 80.8 | |
| DRIFTBase Model=Qwen3-8B, Evaluation Protocol=mean@162026.06 | 80.5 | |
| SRPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Cited from prior work2026.06 | 78.4 | |
| PGPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Cited from prior work2026.06 | 77.6 | |
| SDPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Cited from prior work2026.06 | 75.6 | |
| SDPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Reproduced2026.06 | 72.7 | |
| GRPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Cited from prior work2026.06 | 72.7 | |
| GRPOBase Model=Qwen3-8B, Evaluation Protocol=mean@16, Source=Reproduced2026.06 | 60.6 | |
| Qwen3-8BBase Model=Qwen3-8B, Evaluation Protocol=mean@162026.06 | 59.2 |