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

Evol-Instruct

Benchmarks

Task NameDataset NameSOTA ResultTrend
LLM AlignmentEvol-Instruct
Win Rate51.4
24
Mathematical ReasoningEvol-Instruct
Accuracy65.9
1
Showing 2 of 2 rows