HUMANEVAL dataset

HumanEval: 164 Python coding tasks. The paid private ZIP contains the original dataset, project README, MIT license and checksums. Public preview shows verified aggregate counts only. Run generated code only in a sandbox.

Dataset

HumanEval 代码评估数据集

164 道 Python 编程题，包含官方任务和测试，下载前请阅读 MIT 许可。

164Records

47.8 KBFile size

ZIP / JSONLDelivery formats

Data sample

Field reference

The purchased version's schema snapshot is authoritative.

Data quality

Quality metrics and processing details come from this version's acceptance report.

test_problems164

untrusted_code_must_be_sandboxedtrue

License

Data source and license notices are provided in the delivered archive.

HumanEval Dataset