Safety on StrongReject
99.7Safety RateVanilla SFT
Evaluation Results
| Method | Links | |
|---|---|---|
| Vanilla SFTAlignment Dataset=DirectRefusal, Backbone=s1.1-7B2026.02 | 99.7 | |
| Vanilla SFTAlignment Dataset=STAR-1, Backbone=s1.1-7B2026.02 | 99.7 | |
| DGR SFTAlignment Dataset=DirectRefusal, Backbone=s1.1-7B2026.02 | 98.7 | |
| Vanilla SFTAlignment Dataset=R1-ACT, Backbone=s1.1-7B2026.02 | 98.1 | |
| DGR SFTAlignment Dataset=STAR-1, Backbone=s1.1-7B2026.02 | 98.1 | |
| DGR SFTAlignment Dataset=R1-ACT, Backbone=s1.1-7B2026.02 | 98.1 | |
| Qwen2.5-7B-Instruct2026.02 | 94.6 | |
| s1.1-7B2026.02 | 38 |