Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Alignment (Jailbreak Resistance) on JailbreakBench
Loading...
74
JailbreakBench Score
DSA:LST+:TA
12.64
28.57
44.5
60.43
May 30, 2025
JailbreakBench Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
JailbreakBench Score
DSA:LST+:TA
lambda value=0
2025.05
74
Zephyr LoRA-aligned
lambda value=0
2025.05
66
DSA:LLD:TA
lambda value=0
2025.05
55
Zephyr Base Model
lambda value=1
2025.05
15
Feedback
Search any
task
Search any
task