Safety Evaluation on XSTest Safe v1
96.8AccuracyQwen2.5-7B-Instruct
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-7B-InstructModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 96.8 | |
| o1Model Category=API-based, Evaluation Protocol=LLM-as-a-Judge2025.07 | 90 | |
| DeepSeek-R1-Distill-Qwen-7BModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 89.2 | |
| o3-miniModel Category=API-based, Evaluation Protocol=LLM-as-a-Judge2025.07 | 88.8 | |
| STAIR-SFTModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 86 | |
| ARMORModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 86 | |
| ARMOR-ThinkModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 84.2 | |
| STAIR-DPOModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 71.6 | |
| STAR-1Model Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 68 |