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

SDF

Benchmarks

Task NameDataset NameSOTA ResultTrend
Verbatim Content RecoverySDF Roman Concrete 1.0 (test)
Verbatim Recovery Score5
8
Verbatim Content RecoverySDF Kansas Abortion 1.0 (test)
Verbatim Recovery Score5
8
Verbatim Content RecoverySDF Ignore Comment 1.0 (test)
Verbatim Recovery Score4
8
Verbatim Content RecoverySDF FDA Approval 1.0 (test)
Verbatim Recovery Score5
8
Verbatim Content RecoverySDF Cake Bake 1.0 (test)
Verbatim Recovery Score (1-5)5
8
Showing 5 of 5 rows