Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction Hierarchy Robustness on Tutor Jailbreak sys-user
Loading...
99
Non-violation Rate
GPT-5-Mini-R
95.88
96.69
97.5
98.31
Mar 11, 2026
Non-violation Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Non-violation Rate
GPT-5-Mini-R
2026.03
99
GPT-5-Mini
2026.03
96
Feedback
Search any
task
Search any
task