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

Code Generation Benchmarks

Benchmarks

Task NameDataset NameSOTA ResultTrend
Code GenerationCode Generation Benchmarks MBPP, MBPP+, BCB-f, BCB-h, LCB
MBPP Score88.9
10
Code GenerationCode Generation Benchmarks Textual
HumanEval+84.1
4
Showing 2 of 2 rows