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

DecTest

Benchmarks

Task NameDataset NameSOTA ResultTrend
Story GenerationDecTest story_gen no_hds (1000 samples)
Spearman ρ0.779
7
Response GenerationDecTest resp_gen no_hds (1000 samples)
Spearman ρ0.924
7
Prompt GenerationDecTest prompt_gen 1000 samples no_hds
Spearman Rho0.932
7
Showing 3 of 3 rows