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

LIFEBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Length FollowingLIFEBench
LD Score10.8
28
Length-controlled text generationLIFEBench
Equal To Length Deviation44
15
Instruction FollowingLIFEBench
Score57.6
4
Showing 3 of 3 rows