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

Preference Classification on Helpfulness & Harmlessness (HH) (test)

70.4Classification Accuracy

BTPO

62.39264.47166.5568.629Oct 17, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
70.4
2025.10
64.7
2025.10
62.7
2025.10
62.7