Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Content Detection on Standard non-adversarial dataset Tax Authority
Loading...
100
TPR
GPT-4
85.44
89.22
93
96.78
Jan 27, 2026
TPR
FPR
Updated 5mo ago
Evaluation Results
Method
Method
Links
TPR
FPR
GPT-4
Rule Definitions=None
2026.01
100
0
GPT-4
Rule Definitions=Included
2026.01
96
2
GAVEL
2026.01
86
0
Feedback
Search any
task
Search any
task
