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

Content Moderation on UnsafeBench Sexual category (test)

81.4Accuracy

KidsNanny (Stage 1+2)

58.114464.159770.20576.2503Mar 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
81.486.1683.2289.31
2026.03
80.3684.5686.1783.02
2026.03
80.2785.3982.0589.02
2026.03
77.0481.1286.8176.13
2026.03
68.9873.981.2367.79
2026.03
68.0376.0173.9678.18
2026.03
64.876.6864.9693.56
2026.03
59.0156.2891.1540.7