Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Content Detection on Standard non-adversarial dataset Delusional
Loading...
90
TPR
GAVEL
83.76
85.38
87
88.62
Jan 27, 2026
TPR
FPR
Updated 5mo ago
Evaluation Results
Method
Method
Links
TPR
FPR
GAVEL
2026.01
90
1
GPT-4
Rule Definitions=Included
2026.01
90
0
GPT-4
Rule Definitions=None
2026.01
84
1
Feedback
Search any
task
Search any
task
