{"url":"/dataset/xcodeeval","name":"xCodeEval","full_name":"xCodeEval","description_markdown":"xCodeEval is one of the largest **executable** multilingual multitask benchmarks consisting of 17 programming languages with execution-level parallelism. It features a total of seven tasks involving code understanding, generation, translation, and retrieval, and **it employs an execution-based evaluation** instead of traditional lexical approaches. It also provides a test-case-based multilingual code execution engine, [ExecEval](https://github.com/ntunlp/ExecEval) that supports all the programming languages in xCodeEval.","description_withheld":null,"homepage":"https://github.com/ntunlp/xCodeEval","introduced_date":"2023-03-06","introduced_date_note":null,"introduced_by":{"paper":"/paper/xcodeeval-a-large-scale-multilingual","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","first_author":"Mohammad Abdullah Matin Khan","url":null},"license":{"name":"cc-by-nc-4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Retrieval","url":"/task/retrieval","datasets_with_task":"/datasets/task/retrieval"},{"name":"Program Synthesis","url":"/task/program-synthesis","datasets_with_task":"/datasets/task/program-synthesis"},{"name":"Program Repair","url":"/task/program-repair","datasets_with_task":"/datasets/task/program-repair"},{"name":"Code Translation","url":"/task/code-translation","datasets_with_task":"/datasets/task/code-translation"},{"name":"Code Classification","url":"/task/code-classification","datasets_with_task":"/datasets/task/code-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["xCodeEval"],"data_loaders":[],"num_papers_in_archive":15,"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."}