Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreaking on JailbreakBench
Loading...
1
Jailbroken Behaviors (k)
PAIR with RT mutator LLM
-0.6
10.2
21
31.8
Dec 9, 2025
Jailbroken Behaviors (k)
Successful Jailbreaks (n)
Self-BLEU
Updated 4d ago
Evaluation Results
Method
Method
Links
Jailbroken Behaviors (k)
Successful Jailbreaks (n)
Self-BLEU
PAIR with RT mutator LLM
Classifier=JailbreakBe...
2025.12
1
1
-
PAIR
Classifier=JailbreakBe...
2025.12
4
-
-
Rainbow Teaming
Classifier=JailbreakBe...
2025.12
7
8
-
PAIR with RT mutator LLM
Classifier=Llama Guard...
2025.12
11
14
-
Rainbow Teaming
Classifier=Llama Guard...
2025.12
41
66
-
PAIR with RT mutator LLM
Description=Prompt div...
2025.12
-
-
0.74
Rainbow Teaming
Description=Prompt div...
2025.12
-
-
0.51
Feedback
Search any
task
Search any
task