Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Detection on AdvBench Mistral-7B
Loading...
99
AUROC
MTK
33.168
50.259
67.35
84.441
Jun 5, 2026
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
MTK
Attack=AutoDAN
2026.06
99
MTK
Attack=Avg.
2026.06
95.3
SelfDefend
Attack=AutoDAN
2026.06
94.5
HiddenDetect
Attack=AutoDAN
2026.06
85.8
SelfDefend
Attack=Avg.
2026.06
84.8
GradCuff
Attack=AutoDAN
2026.06
82
HSF
Attack=Avg.
2026.06
80.8
HiddenDetect
Attack=Avg.
2026.06
78.9
HSF
Attack=AutoDAN
2026.06
71.7
SaP
Attack=Avg.
2026.06
63.5
GradCuff
Attack=Avg.
2026.06
60
SmoothLLM
Attack=Avg.
2026.06
53.7
SaP
Attack=AutoDAN
2026.06
50.5
GradSafe
Attack=Avg.
2026.06
47.3
GradSafe
Attack=AutoDAN
2026.06
43.1
SmoothLLM
Attack=AutoDAN
2026.06
35.7
Feedback
Search any
task
Search any
task