lightonai/HumanEvalPlus_multilingual

HumanEval+ Multilingual 是基准测试HumanEval+的多语言版本，覆盖六种语言：英语、法语、德语、西班牙语、中文和斯瓦希里语。每个样本是一个来自HumanEval+（OpenAI HumanEval的扩展版本，包含更多测试）的Python代码生成问题，自然语言提示被翻译成这五种目标语言。该数据集与论文《Rethinking the Multilingual Reasoning Gap with Layer Swap》一起发布，源基准测试是HumanEval+，专注于具有扩展测试覆盖率的代码生成。

HumanEval+ Multilingual is a multilingual version of the benchmark HumanEval+, covering six languages: English, French, German, Spanish, Chinese, and Swahili. Each sample is a Python code generation problem from HumanEval+ (an extended version of OpenAIs HumanEval with more tests), with the natural-language prompt translated into the five target languages. It is released alongside the paper Rethinking the Multilingual Reasoning Gap with Layer Swap, with the source benchmark being HumanEval+ for code generation with extended test coverage.