{"url":"/dataset/humaneval-x","name":"HumanEval-X","full_name":null,"description_markdown":"HumanEval-X is a benchmark for evaluating the multilingual ability of code generative models. It consists of 820 high-quality human-crafted data samples (each with test cases) in Python, C++, Java, JavaScript, and Go, and can be used for various tasks, such as code generation and translation.","description_withheld":null,"homepage":"https://huggingface.co/datasets/THUDM/humaneval-x","introduced_date":"2023-03-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/codegeex-a-pre-trained-model-for-code","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","first_author":"Qinkai Zheng","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"},{"name":"Code Translation","url":"/task/code-translation","datasets_with_task":"/datasets/task/code-translation"}],"languages":[],"variants":["HumanEval-X"],"data_loaders":[{"repo":"https://github.com/THUDM/CodeGeeX","url":"https://github.com/THUDM/CodeGeeX/blob/main/codegeex/benchmark/README.md","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}