HumanEvalPlus_multilingual

# HumanEval+ Multilingual `HumanEvalPlus_multilingual` is a multilingual version of the benchmark [HumanEval+](https://huggingface.co/datasets/evalplus/humanevalplus), covering **six languages**: English, French, German, Spanish, Chinese, and Swahili. Each sample is a Python code generation problem from HumanEval+ (an extended version of OpenAI's HumanEval with 80x 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**](https://arxiv.org/abs/2605.26735). ## Dataset details - **Source benchmark:** [HumanEval+](https://huggingface.co/datasets/evalplus/humanevalplus), code generation with extended test coverage. - **Languages:** English (source) + French, German, Spanish, Chinese, Swahili. ## Citation If you find our work helpful, feel free to give us a cite. ```bibtex @misc{lasbordes2026rethinking, title = {Rethinking the Multilingual Reasoning Gap with Layer Swap}, author = {Lasbordes, Maxence and Chatelain, Amélie and Seddah, Djamé}, year = {2026}, eprint = {2605.26735}, archivePrefix= {arXiv}, primaryClass = {cs.CL} } ```