Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Attack Robustness on HarmBench 200 standard behaviors
Loading...
34.5
GCG Success Rate
Initial
1.22
9.86
18.5
27.14
Jun 2, 2026
GCG Success Rate
PAIR Success Rate
TAP Success Rate
AutoDAN Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
GCG Success Rate
PAIR Success Rate
TAP Success Rate
AutoDAN Success Rate
Initial
Model=Llama-2-7b-Chat,...
2026.06
34.5
7.5
5.5
50
Insertion
Model=Llama-2-7b-Chat,...
2026.06
2.5
1
1
0
Feedback
Search any
task
Search any
task
