Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Attack Success Evaluation on IICL Evaluation Set 5 harmful queries
Loading...
0
Average Bypass Rate
IICL
-0.596
3.427
7.45
11.473
Apr 21, 2026
Average Bypass Rate
Attack Success Rate (ASR)
Queries Cracked Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Bypass Rate
Attack Success Rate (ASR)
Queries Cracked Rate
IICL
Target Model=gpt-5
2026.04
0
0
0
IICL
Target Model=gpt-5-mini
2026.04
0
0
0
IICL
Target Model=gpt-5-pro
2026.04
0
0
0
IICL
Target Model=gpt-5.2
2026.04
0
0
0
IICL
Target Model=gpt-5.2-pro
2026.04
0
0
0
IICL
Target Model=gpt-5.4-pro
2026.04
0
0
0
IICL
Target Model=gpt-5.4
2026.04
1.7
60
60
IICL
Target Model=gpt-5.1
2026.04
4.2
60
60
IICL
Target Model=gpt-4o
2026.04
14.3
100
100
IICL
Target Model=gpt-4.1
2026.04
14.9
100
100
Feedback
Search any
task
Search any
task