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

MBPP+

Benchmarks

Task NameDataset NameSOTA ResultTrend
Unit test generationMBPP+ (test)
Error Rate0.53
7
Code GenerationMBPP+ full latest
TPF670
3
Code GenerationMBPP+ 0-shot
Accuracy79.36
3
Showing 3 of 3 rows