Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Robustness on PAIR v1 (test)
Loading...
15.6
Compliance Rate
Qwen2.5-7B-Instruct
1.04
4.82
8.6
12.38
Jul 14, 2025
Compliance Rate
Updated 18d ago
Evaluation Results
Method
Method
Links
Compliance Rate
Qwen2.5-7B-Instruct
Model Category=Local,...
2025.07
15.6
o3-mini
Model Category=API-bas...
2025.07
11.2
o1
Model Category=API-bas...
2025.07
8.4
DeepSeek-R1-Distill-Qwen-7B
Model Category=Local,...
2025.07
8
STAR-1
Model Category=Local,...
2025.07
8
STAIR-SFT
Model Category=Local,...
2025.07
6
STAIR-DPO
Model Category=Local,...
2025.07
4.8
ARMOR-Think
Model Category=Local,...
2025.07
2
ARMOR
Model Category=Local,...
2025.07
1.6
Feedback
Search any
task
Search any
task