Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction Hierarchy Robustness on System <> User Conflict
Loading...
95
Non-violation Rate
GPT-5-Mini-R
83.56
86.53
89.5
92.47
Mar 11, 2026
Non-violation Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Non-violation Rate
GPT-5-Mini-R
2026.03
95
GPT-5-Mini
2026.03
84
Feedback
Search any
task
Search any
task