List your company

Code Generation

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated
85.75Accuracy
Code Generation on MBPP+ performance trend
243
Jun 15, 2026
84.39Pass@1
Code Generation on MBPP+ (pass@1) performance trend
238
Jun 1, 2026
97.56Accuracy
Code Generation on HumanEval (Acc, TPF, AUP) performance trend
224
Jun 4, 2026
98.27Accuracy
Code Generation on HumanEval (Accuracy, Exit Position) performance trend
212
Jun 19, 2026
89.1Pass@1
Code Generation on MBPP (pass@1, pass@80) performance trend
193
Mar 16, 2026
8.99Average Acceptance Length (τ)
95
Jul 1, 2026