Safety Evaluation on Harmful Questions
0ASR (None)STAR1-R1-Distill-7B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| STAR1-R1-Distill-7BModel Series=7B Models, Safety Training Data=10002025.05 | 0 | 14 | 42 | 18.7 | |
| RealSafe-R1-7BModel Series=7B Models, Safety Training Data=150002025.05 | 0 | 2 | 8 | 3.3 | |
| STAR1-R1-Distill-32BModel Series=32B Models, Safety Training Data=10002025.05 | 0 | 12 | 46 | 19.3 | |
| RealSafe-R1-32BModel Series=32B Models, Safety Training Data=150002025.05 | 0 | 4 | 12 | 5.3 | |
| Improved CoTModel Series=32B Models, Safety Training Data=10002025.05 | 0 | 2 | 8 | 3.3 | |
| Improved CoTModel Series=7B Models, Safety Training Data=10002025.05 | 4 | 4 | 12 | 6.7 |