List your company

Jailbreak Robustness on PAIR v1 (test)

15.6Compliance RateQwen2.5-7B-Instruct
1.044.828.612.38Jul 14, 2025

Evaluation results

MethodLinks
Qwen2.5-7B-InstructModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.0715.6
o3-miniModel Category=API-based, Evaluation Protocol=LLM-as-a-Judge2025.0711.2
o1Model Category=API-based, Evaluation Protocol=LLM-as-a-Judge2025.078.4
DeepSeek-R1-Distill-Qwen-7BModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.078
STAR-1Model Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.078
STAIR-SFTModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.076
STAIR-DPOModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.074.8
ARMOR-ThinkModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.072
ARMORModel Category=Local, Evaluation Protocol=LLM-as-a-Judge2025.071.6