Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Over-refusal Compliance on OK Seemingly Toxic
Loading...
86
Compliance Rate (Keyword Filter)
DCR
74.56
77.53
80.5
83.47
Feb 10, 2026
Compliance Rate (Keyword Filter)
Compliance Rate (GPT-4o Judge)
Compliance Rate (GPT 5.1 Judge)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Compliance Rate (Keyword Filter)
Compliance Rate (GPT-4o Judge)
Compliance Rate (GPT 5.1 Judge)
DCR
2026.02
86
94
94
SCANS
2026.02
84
86
89
Surgical
2026.02
78
74
90
STL-aug
2026.02
76
86
79
STL
2026.02
75
84
76
Feedback
Search any
task
Search any
task
