{"url":"/dataset/odex","name":"ODEX","full_name":null,"description_markdown":"ODEX is an open-domain 📖, multilingual 🌍, execution-based 🛠 natural language to code generation 💻 data benchmark. ODEX has 945 NL-Code pairs spanning 79 diverse libraries, along with 1,707 human-written test cases for execution. The NL-Code pairs are harvested from StackOverflow forums to encourage natural and practical coding queries. Moreover, ODEX supports four natural languages as intents: English, español (Spanish), 日本語 (Japanese), and Pусский (Russian).","description_withheld":null,"homepage":"https://code-eval.github.io/","introduced_date":"2022-12-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/execution-based-evaluation-for-open-domain","title":"Execution-Based Evaluation for Open-Domain Code Generation","first_author":"Zhiruo Wang","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["ODEX"],"data_loaders":[],"num_papers_in_archive":18,"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."}