Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Over-refusal Compliance on OR Seemingly Toxic
Loading...
87
Compliance Rate (Keyword Filter)
SCANS
52.68
61.59
70.5
79.41
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)
SCANS
2026.02
87
82
83
DCR
2026.02
83
80
80
STL
2026.02
72
70
65
STL-aug
2026.02
69
65
60
Surgical
2026.02
54
46
50
Feedback
Search any
task
Search any
task