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

HUMANUAL

Benchmarks

Task NameDataset NameSOTA ResultTrend
Response AlignmentHUMANUAL (test)
Alignment Score (Chat)6.08
8
User SimulationHUMANUAL (test)
News Score40.58
3
Showing 2 of 2 rows