Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MBPP EvalPlus

Benchmarks

Task NameDataset NameSOTA ResultTrend
Code GenerationMBPP EvalPlus base
Pass@190.5
11
Program SynthesisMBPP-EvalPlus Standard (test)
Pass@179.9
2
Showing 2 of 2 rows