{"url":"/dataset/spider-2-0","name":"Spider 2.0","full_name":"Spider 2.0","description_markdown":"Spider 2.0 is a comprehensive code generation agent task that includes 632 examples. The agent has to interactively explore various types of databases, such as BigQuery, Snowflake, Postgres, ClickHouse, DuckDB, and SQLite. It is required to engage with complex SQL workflows, process extensive contexts, perform intricate reasoning, and generate multiple SQL queries with diverse operations, often exceeding 100 lines across multiple interactions.","description_withheld":null,"homepage":"https://spider2-sql.github.io/","introduced_date":"2024-11-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/spider-2-0-evaluating-language-models-on-real","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","first_author":"Fangyu Lei","url":null},"license":{"name":"Apache 2.0","url":"https://github.com/xlang-ai/Spider2/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Environment","url":"/datasets/modality/environment"}],"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":["Spider 2.0"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-to-sql-on-spider-2-0","task":"Text-To-SQL","dataset_variant":"Spider 2.0","rows":8,"metrics":["Success Rate"],"first_row_in_archive_order":{"model":"Spider-Agent + o1-preview","paper":"/paper/spider-2-0-evaluating-language-models-on-real","metrics":{"Success Rate":"17.03"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/spider-2-0-evaluating-language-models-on-real","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","date":"2024-11-12","rows_on_this_dataset":8,"code_links":0,"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."}