{"url":"/sota/mmsql-performance-on-mmsql","task":{"name":"MMSQL performance","url":"/task/mmsql-performance","note":null},"dataset":{"name":"MMSQL","url":"/dataset/mmsql"},"category":"Natural Language Processing","categories":["Computer Code","Natural Language Processing"],"category_note":null,"description":"To measure the performance of a model in handling various types of multi-turn text-to-SQL scenarios.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["TDEX"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"TDEX":null}},"counts":{"rows":6,"rows_with_code":6,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"GPT-4 Turbo","metrics":{"TDEX":"67.0"},"uses_additional_data":false,"paper_date":"2024-12-21","paper":"/paper/evaluating-and-enhancing-llms-for-multi-turn","paper_url":"https://arxiv.org/abs/2412.17867v1","paper_title":"Evaluating and Enhancing LLMs for Multi-turn Text-to-SQL with Multiple Question Types","code":"https://github.com/mcxiaoxiao/MMSQL","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Gemini-1.5 Flash","metrics":{"TDEX":"65.8"},"uses_additional_data":false,"paper_date":"2024-12-21","paper":"/paper/evaluating-and-enhancing-llms-for-multi-turn","paper_url":"https://arxiv.org/abs/2412.17867v1","paper_title":"Evaluating and Enhancing LLMs for Multi-turn Text-to-SQL with Multiple Question Types","code":"https://github.com/mcxiaoxiao/MMSQL","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"GPT-3.5 Turbo","metrics":{"TDEX":"64.1"},"uses_additional_data":false,"paper_date":"2024-12-21","paper":"/paper/evaluating-and-enhancing-llms-for-multi-turn","paper_url":"https://arxiv.org/abs/2412.17867v1","paper_title":"Evaluating and Enhancing LLMs for Multi-turn Text-to-SQL with Multiple Question Types","code":"https://github.com/mcxiaoxiao/MMSQL","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Llama3-8B","metrics":{"TDEX":"64.0"},"uses_additional_data":false,"paper_date":"2024-12-21","paper":"/paper/evaluating-and-enhancing-llms-for-multi-turn","paper_url":"https://arxiv.org/abs/2412.17867v1","paper_title":"Evaluating and Enhancing LLMs for Multi-turn Text-to-SQL with Multiple Question Types","code":"https://github.com/mcxiaoxiao/MMSQL","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Llama3-70B","metrics":{"TDEX":"62.8"},"uses_additional_data":false,"paper_date":"2024-12-21","paper":"/paper/evaluating-and-enhancing-llms-for-multi-turn","paper_url":"https://arxiv.org/abs/2412.17867v1","paper_title":"Evaluating and Enhancing LLMs for Multi-turn Text-to-SQL with Multiple Question Types","code":"https://github.com/mcxiaoxiao/MMSQL","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"SQLCoder-8B","metrics":{"TDEX":"30.7"},"uses_additional_data":false,"paper_date":"2024-12-21","paper":"/paper/evaluating-and-enhancing-llms-for-multi-turn","paper_url":"https://arxiv.org/abs/2412.17867v1","paper_title":"Evaluating and Enhancing LLMs for Multi-turn Text-to-SQL with Multiple Question Types","code":"https://github.com/mcxiaoxiao/MMSQL","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}