2000 character limit reached
AixBench: A Code Generation Benchmark Dataset (2206.13179v2)
Published 27 Jun 2022 in cs.SE
Abstract: We present a benchmark dataset for evaluating method-level code generation task. The benchmark contains a dataset of 175 samples for automated evaluation and a dataset of 161 samples for manual evaluation. We also present a new metric for automatically evaluating the correctness of the generated code, and a set of criteria to manually evaluating the overall quality of the generated code.