List your company

Code Generation

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated
94.2Pass@1 Accuracy
Code Generation on MBPP (pass@1 accuracy) performance trend
59
Mar 9, 2026
84.6Pass@1 Accuracy
Code Generation on MBPP (Acc, TPF, AUP) performance trend
55
Jun 18, 2026