{"url":"/dataset/webapp1k-react","name":"WebApp1K-React","full_name":null,"description_markdown":"Test-driven benchmark to challenge LLMs to write JavaScript React application\r\n\r\n[GitHub Script](https://github.com/onekq/WebApp1k)","description_withheld":null,"homepage":"https://huggingface.co/datasets/onekq-ai/WebApp1K-React","introduced_date":"2024-07-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/2408-00019","title":"WebApp1K: A Practical Code-Generation Benchmark for Web App Development","first_author":"Yi Cui","url":null},"license":{"name":"mit","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WebApp1K-React"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/code-generation-on-webapp1k-react","task":"Code Generation","dataset_variant":"WebApp1K-React","rows":8,"metrics":["pass@1"],"first_row_in_archive_order":{"model":"o1-preview","paper":"/paper/a-case-study-of-web-app-coding-with-openai","metrics":{"pass@1":"0.952"},"code_links":[{"title":"onekq/webapp1k","url":"https://github.com/onekq/webapp1k"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/a-case-study-of-web-app-coding-with-openai","title":"A Case Study of Web App Coding with OpenAI Reasoning Models","date":"2024-09-19","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/insights-from-benchmarking-frontier-language","title":"Insights from Benchmarking Frontier Language Models on Web App Code Generation","date":"2024-09-08","rows_on_this_dataset":5,"code_links":1,"syntology":null}],"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."}