Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Harmful prompt detection on OpenAI

79.11F1 Score

LlamaGuard3

64.009267.929671.8575.7704Feb 22, 2025
Updated 1d ago

Evaluation Results

MethodLinks
2025.02
79.11
2025.02
77.63
2025.02
77.63
2025.02
76.44
2025.02
75.69
2025.02
75.19
2025.02
74.56
2025.02
74.21
2025.02
72.85
2025.02
72.35
2025.02
72.28
2025.02
70.68
2025.02
68.45
2025.02
67.99
2025.02
66.95
2025.02
66.6
2025.02
64.59