Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Attack on HarmBench standard behaviors
Loading...
61
ASR
AdvGRPO
59.9
67.325
74.75
82.175
Jun 8, 2026
ASR
Updated 1mo ago
Evaluation Results
Method
Method
Links
ASR
AdvGRPO
Transfer Defender=Llam...
2026.06
61
AdvGRPO
Transfer Defender=Phi-...
2026.06
67.5
AdvGRPO
Transfer Defender=Gemm...
2026.06
68.5
SEMA
Transfer Defender=Phi-...
2026.06
71.5
SEMA
Transfer Defender=Gemm...
2026.06
75.5
SEMA
Transfer Defender=Llam...
2026.06
79.5
AdvGRPO
Transfer Defender=Phi-...
2026.06
82
AdvGRPO
Transfer Defender=Gemm...
2026.06
86
AdvGRPO
Transfer Defender=Llam...
2026.06
88.5
Feedback
Search any
task
Search any
task
