List your company

Misuse Detection on Misuse Categories Scam (Tax Authority)

99AUCLlama Guard 4 (Meta)
-2.9223.545076.46Jan 27, 2026

Evaluation results

MethodLinks
Llama Guard 4 (Meta)Category=Moderation, Base Model=Mistral-7B2026.0199990
Activation ClassifierCategory=Classifier, Base Model=Mistral-7B2026.0199991
GAVELCategory=Classifier, Base Model=Mistral-7B2026.0199922
RepBendingCategory=Fine-Tuning, Base Model=Mistral-7B2026.0198992
Circuit BreakersCategory=Fine-Tuning, Base Model=Mistral-7B2026.0167681
Moderator (OpenAI)Category=Moderation, Base Model=Mistral-7B2026.0150500
JBShieldCategory=Inference-Time, Base Model=Mistral-7B2026.0114560
CASTCategory=Inference-Time, Base Model=Mistral-7B2026.0182491
Perspective (Google)Category=Moderation, Base Model=Mistral-7B2026.011490