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

Chat and Instruction-following Suite

Benchmarks

Task NameDataset NameSOTA ResultTrend
Instruction following and reasoningChat and Instruction-following Suite IFEval, AE2, MTB, GSM8K
IFEval0.695
5
Showing 1 of 1 rows