Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-turn Jailbreak on AdvBench
Loading...
98
ASR (X-Teaming)
No Defense
-3.712
22.694
49.1
75.506
Jun 1, 2026
ASR (X-Teaming)
ASR (Tempest)
Updated 1d ago
Evaluation Results
Method
Method
Links
ASR (X-Teaming)
ASR (Tempest)
No Defense
Model=Qwen2.5-7B, Defe...
2026.06
98
90
No Defense
Model=Llama3-8B, Defen...
2026.06
92
73
SAGE
Model=Qwen2.5-7B, Defe...
2026.06
83.6
2.8
PROACT
Model=Qwen2.5-7B, Defe...
2026.06
67
3.1
PROACT
Model=Llama3-8B, Defen...
2026.06
24
2.5
SAGE
Model=Llama3-8B, Defen...
2026.06
21.2
3.5
THRD
Model=Qwen2.5-7B, Defe...
2026.06
1.3
0.5
THRD
Model=Llama3-8B, Defen...
2026.06
0.2
1
Feedback
Search any
task
Search any
task