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

Prompt Harmfulness Classification on WILDGUARD (test)

88.9F1 (Total)

WILDGUARD

6.2227.68549.1570.615Jun 26, 2024Aug 6, 2024Sep 16, 2024Oct 27, 2024Dec 7, 2024Jan 17, 2025Feb 28, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2024.06
88.985.591.7
2024.06
87.981.693.4
2024.06
78.574.582
2024.06
71.562.977.9
70.946.185.6
2025.02
61.7--
2025.02
57.2--
5632.670.5
2025.02
56--
12.16.816.3
2025.02
12.1--
2025.02
9.4--