Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Robustness on StrongReject Static PAIR threshold 0.75 (test)
Loading...
0
ASR
BCT
-1.512
8.694
18.9
29.106
May 20, 2026
ASR
1 - ASR
Updated 12d ago
Evaluation Results
Method
Method
Links
ASR
1 - ASR
BCT
Model=Qwen3-4B-Instruc...
2026.05
0
100
OPCT
Model=Qwen3-4B-Instruc...
2026.05
0
100
OPCT
Model=Qwen3-8B, Strong...
2026.05
0
100
BCT
Model=gpt-oss-20b, Str...
2026.05
0
100
OPCT
Model=gpt-oss-20b, Str...
2026.05
1.1
98.9
BCT
Model=Qwen3-8B, Strong...
2026.05
4.1
95.9
Baseline
Model=Qwen3-4B-Instruc...
2026.05
31.6
68.4
Baseline
Model=gpt-oss-20b, Str...
2026.05
36.2
63.8
Baseline
Model=Qwen3-8B, Strong...
2026.05
37.8
62.2
Feedback
Search any
task
Search any
task