Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Misuse Detection on Misuse Categories Scam (Romance)
Loading...
100
AUC
Activation Classifier
-4
23
50
77
Jan 27, 2026
AUC
Balanced Accuracy
FPR
Updated 4d ago
Evaluation Results
Method
Method
Links
AUC
Balanced Accuracy
FPR
Activation Classifier
Category=Classifier, B...
2026.01
100
98
0
GAVEL
Category=Classifier, B...
2026.01
99
100
0
RepBending
Category=Fine-Tuning,...
2026.01
91
92
3
Llama Guard 4 (Meta)
Category=Moderation, B...
2026.01
89
94
3
Circuit Breakers
Category=Fine-Tuning,...
2026.01
50
51
0
Moderator (OpenAI)
Category=Moderation, B...
2026.01
50
50
0
CAST
Category=Inference-Tim...
2026.01
39
44
85
JBShield
Category=Inference-Tim...
2026.01
1
50
0
Perspective (Google)
Category=Moderation, B...
2026.01
0
50
0
Feedback
Search any
task
Search any
task