Safety Evaluation on HarmBench Hades
1Safety Score (1-ASR)RESTA
Evaluation Results
| Method | Links | |
|---|---|---|
| RESTABackbone Model=Lingshu-7B2025.12 | 1 | |
| PSIBackbone Model=HuatuoGPT-Vision-7B2025.12 | 0.9075 | |
| RESTABackbone Model=HuatuoGPT-Vision-7B2025.12 | 0.875 | |
| PSIBackbone Model=Lingshu-7B2025.12 | 0.87 | |
| OriginalBackbone Model=Lingshu-7B2025.12 | 0.4275 | |
| ModelMergeBackbone Model=Lingshu-7B2025.12 | 0.425 | |
| ModelMergeBackbone Model=HuatuoGPT-Vision-7B2025.12 | 0.21 | |
| OriginalBackbone Model=HuatuoGPT-Vision-7B2025.12 | 0.1975 |