{"url":"/dataset/xlcost","name":"XLCoST","full_name":"Cross-Lingual Code Snippet","description_markdown":"**XLCoST** is a benchmark dataset for cross-lingual code intelligence. The dataset contains fine-grained parallel data from 8 languages (7 commonly used programming languages and English), and supports 10 cross-language code tasks.\r\n\r\nSource: [XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence](https://arxiv.org/pdf/2206.08474v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2206.08474v1.pdf](https://arxiv.org/pdf/2206.08474v1.pdf)","description_withheld":null,"homepage":"https://github.com/reddy-lab-code-research/XLCoST","introduced_date":"2022-06-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/xlcost-a-benchmark-dataset-for-cross-lingual","title":"XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence","first_author":"Ming Zhu","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/reddy-lab-code-research/XLCoST/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Code Search","url":"/task/code-search","datasets_with_task":"/datasets/task/code-search"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["XLCoST"],"data_loaders":[],"num_papers_in_archive":22,"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."}