List your company

HumanEval

Benchmarks

TaskDatasetSOTA resultTrendResults
HumanEval (test)
100Pass@1
Code Generation on HumanEval (test) performance trend
701
HumanEval+
100Pass@1
Code Generation on HumanEval+ performance trend
393
HumanEval
97.56Accuracy
Code Generation on HumanEval (Acc, TPF, AUP) performance trend
224
HumanEval
98.27Accuracy
Code Generation on HumanEval (Accuracy, Exit Position) performance trend
212
HumanEval
98.17Pass@1
Coding on HumanEval performance trend
168
HumanEval+
95.12Pass@1
164
HumanEval 1.0 (test)
85.4Pass@1
Code Generation on HumanEval 1.0 (test) performance trend
145
HumanEval
96.34HumanEval Accuracy
Code on HumanEval (Accuracy) performance trend
118
HumanEval
95.62Accuracy
84