Science Question Answering on Biology (Bio.)
65.4Mean@16SC-SDPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SC-SDPOBackbone=Qwen3-8B, Alpha=0.52026.05 | 65.4 | 68.5 | |
| SDPOBackbone=Qwen3-8B2026.05 | 60.4 | 61.9 | |
| GRPOBackbone=Qwen3-8B2026.05 | 58.9 | 60 | |
| SC-SDPOBackbone=Qwen3-8B, Alpha=12026.05 | 58.1 | 56.3 | |
| SDPOBackbone=Qwen3-8B, Weighting Strategy=PACED2026.05 | 57 | 59 | |
| SDPOBackbone=Qwen3-8B, Filtering Strategy=Hard Filter2026.05 | 56 | 56.4 | |
| SRPOBackbone=Qwen3-8B2026.05 | 56 | 60.8 | |
| GRPOBackbone=Qwen3-8B, Normalization=None2026.05 | 53.2 | 53.9 | |
| Qwen3-8BBackbone=Qwen3-8B2026.05 | 28.7 | 14 |