Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Attack Detection on Harmful Attacks 105K sample set

97.4Detection Rate

LlamaGuard

3.48827.86952.2576.631Feb 15, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
97.4
2026.02
85.8
2026.02
68
2026.02
67
2026.02
37.3
2026.02
36.7
2026.02
27.4
2026.02
7.1