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

ComplexBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Instruction FollowingComplexBench
Overall Score85.22
43
Instruction FollowingComplexBench Out-of-Domain
Overall Score79.8
23
Showing 2 of 2 rows