Jailbreak Robustness on AdvBench AdvReasoning (original)
6ASRARMOR-Think
Evaluation results
| Method | Links | |
|---|---|---|
| ARMOR-ThinkModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 6 | |
| ARMORModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 8 | |
| STAIR-DPOModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 52 | |
| o3-miniModel Category=API-based, Evaluation Protocol=LLM-as-a-Judge2025.07 | 58 | |
| o1Model Category=API-based, Evaluation Protocol=LLM-as-a-Judge2025.07 | 66 | |
| STAIR-SFTModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 78 | |
| DeepSeek-R1-Distill-Qwen-7BModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 88 | |
| STAR-1Model Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 88 | |
| Qwen2.5-7B-InstructModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.07 | 98 |