{"url":"/dataset/sql-eval-1","name":"SQL-Eval","full_name":null,"description_markdown":"SQL-Eval is an open-source PostgreSQL evaluation dataset released by Defog, constructed based on Spider. The original link can be found at https://github.com/defog-ai/sql-eval. \r\nOur evaluation methodology is more stringent, as it compares the execution accuracy of the predicted SQL queries against the sole ground truth SQL query.","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text-To-SQL","url":"/task/text-to-sql","datasets_with_task":"/datasets/task/text-to-sql"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SQL-Eval"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-to-sql-on-sql-eval-1","task":"Text-To-SQL","dataset_variant":"SQL-Eval","rows":1,"metrics":["Execution Accuracy"],"first_row_in_archive_order":{"model":"XiYan-SQL","paper":"/paper/xiyan-sql-a-multi-generator-ensemble","metrics":{"Execution Accuracy":"69.86"},"code_links":[{"title":"XGenerationLab/XiYan-SQL","url":"https://github.com/XGenerationLab/XiYan-SQL"},{"title":"xgenerationlab/xiyan_mcp_server","url":"https://github.com/xgenerationlab/xiyan_mcp_server"},{"title":"XGenerationLab/M-Schema","url":"https://github.com/XGenerationLab/M-Schema"},{"title":"xgenerationlab/xiyan-dbdescgen","url":"https://github.com/xgenerationlab/xiyan-dbdescgen"},{"title":"XGenerationLab/XiYan-DateResolver","url":"https://github.com/XGenerationLab/XiYan-DateResolver"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/xiyan-sql-a-multi-generator-ensemble","title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","date":"2024-11-13","rows_on_this_dataset":1,"code_links":5,"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."}