{"url":"/sota/text-to-sql-on-spider","task":{"name":"Text-To-SQL","url":"/task/text-to-sql","note":null},"dataset":{"name":"spider","url":"/dataset/spider-realistic"},"category":"Natural Language Processing","categories":["Computer Code","Natural Language Processing"],"category_note":null,"description":"**Text-to-SQL** is a task in natural language processing (NLP) where the goal is to automatically generate SQL queries from natural language text. The task involves converting the text input into a structured representation and then using this representation to generate a semantically correct SQL query that can be executed on a database.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [SyntaxSQLNet](https://arxiv.org/pdf/1810.05237v2.pdf) )</span>","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":["Execution Accuracy (Test)","Exact Match Accuracy (Test)","Execution Accuracy (Dev)","Exact Match Accuracy (Dev)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Execution Accuracy (Test)":"higher","Exact Match Accuracy (Test)":"higher","Execution Accuracy (Dev)":"higher","Exact Match Accuracy (Dev)":"higher"}},"counts":{"rows":20,"rows_with_code":17,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"XiYan-SQL","metrics":{"Execution Accuracy (Test)":"89.65"},"uses_additional_data":false,"paper_date":"2024-11-13","paper":"/paper/xiyan-sql-a-multi-generator-ensemble","paper_url":"https://arxiv.org/abs/2411.08599v3","paper_title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","code":"https://github.com/XGenerationLab/XiYan-SQL","n_code_links":5,"syntology":null},{"rank_in_archive_order":2,"model":"PET-SQL","metrics":{"Exact Match Accuracy (Test)":"66.6","Execution Accuracy (Test)":"87.6"},"uses_additional_data":false,"paper_date":"2024-03-13","paper":"/paper/pet-sql-a-prompt-enhanced-two-stage-text-to","paper_url":"https://arxiv.org/abs/2403.09732v4","paper_title":"PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency","code":"https://github.com/zhshlii/petsql","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":3,"model":"DAIL-SQL + GPT-4 + Self-Consistency","metrics":{"Exact Match Accuracy (Dev)":"74.4","Execution Accuracy (Dev)":"84.4","Execution Accuracy (Test)":"86.6"},"uses_additional_data":false,"paper_date":"2023-08-29","paper":"/paper/text-to-sql-empowered-by-large-language","paper_url":"https://arxiv.org/abs/2308.15363v4","paper_title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","code":"https://github.com/beachwang/dail-sql","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"DIN-SQL + GPT-4","metrics":{"Exact Match Accuracy (Test)":"60","Execution Accuracy (Test)":"85.3"},"uses_additional_data":false,"paper_date":"2023-04-21","paper":"/paper/din-sql-decomposed-in-context-learning-of-1","paper_url":"https://arxiv.org/abs/2304.11015v3","paper_title":"DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction","code":"https://github.com/mohammadrezapourreza/few-shot-nl2sql-with-prompting","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"MSc-SQL","metrics":{"Execution Accuracy (Test)":"84.7"},"uses_additional_data":false,"paper_date":"2024-10-16","paper":"/paper/msc-sql-multi-sample-critiquing-small","paper_url":"https://arxiv.org/abs/2410.12916v1","paper_title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","code":"https://github.com/layer6ai-labs/msc-sql","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":0,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"MARLO + Claude 2.1","metrics":{"Execution Accuracy (Dev)":"83.6","Execution Accuracy (Test)":"84.0"},"uses_additional_data":false,"paper_date":"2024-10-17","paper":"/paper/learning-metadata-agnostic-representations","paper_url":"https://arxiv.org/abs/2410.14049v1","paper_title":"Learning Metadata-Agnostic Representations for Text-to-SQL In-Context Example Selection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"C3 + ChatGPT + Zero-Shot","metrics":{"Execution Accuracy (Dev)":"81.8","Execution Accuracy (Test)":"82.3"},"uses_additional_data":false,"paper_date":"2023-07-14","paper":"/paper/c3-zero-shot-text-to-sql-with-chatgpt","paper_url":"https://arxiv.org/abs/2307.07306v1","paper_title":"C3: Zero-shot Text-to-SQL with ChatGPT","code":"https://github.com/bigbigwatermalon/c3sql","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"RESDSQL-3B + NatSQL","metrics":{"Exact Match Accuracy (Dev)":"80.5","Exact Match Accuracy (Test)":"72.0","Execution Accuracy (Dev)":"84.1","Execution Accuracy (Test)":"79.9"},"uses_additional_data":false,"paper_date":"2023-02-12","paper":"/paper/decoupling-the-skeleton-parsing-and-schema","paper_url":"https://arxiv.org/abs/2302.05965v3","paper_title":"RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL","code":"https://github.com/ruckbreasoning/resdsql","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"T5-3B+NatSQL+Token Preprocessing","metrics":{"Exact Match Accuracy (Dev)":"69.4","Execution Accuracy (Dev)":"73.7","Execution Accuracy (Test)":"78"},"uses_additional_data":false,"paper_date":"2023-05-27","paper":"/paper/improving-generalization-in-language-model","paper_url":"https://arxiv.org/abs/2305.17378v1","paper_title":"Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniques","code":"https://github.com/dakingrai/ood-generalization-semantic-boundary-techniques","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"Graphix-3B+PICARD","metrics":{"Exact Match Accuracy (Dev)":"77.1","Execution Accuracy (Dev)":"81.0","Execution Accuracy (Test)":"77.6"},"uses_additional_data":false,"paper_date":"2023-01-18","paper":"/paper/graphix-t5-mixing-pre-trained-transformers","paper_url":"https://arxiv.org/abs/2301.07507v1","paper_title":"Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing","code":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/graphix","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"T5-SR","metrics":{"Exact Match Accuracy (Dev)":"77.2","Exact Match Accuracy (Test)":"72.4","Execution Accuracy (Test)":"75.2"},"uses_additional_data":false,"paper_date":"2023-06-14","paper":"/paper/t5-sr-a-unified-seq-to-seq-decoding-strategy","paper_url":"https://arxiv.org/abs/2306.08368v1","paper_title":"T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing","code":"https://github.com/JuruoMP/T5-SR","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"T5-3B + PICARD","metrics":{"Exact Match Accuracy (Dev)":"75.5","Exact Match Accuracy (Test)":"71.9 ","Execution Accuracy (Test)":"75.1"},"uses_additional_data":false,"paper_date":"2021-09-10","paper":"/paper/picard-parsing-incrementally-for-constrained","paper_url":"https://arxiv.org/abs/2109.05093v1","paper_title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","code":"https://github.com/servicenow/picard","n_code_links":3,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"SADGA + GAP","metrics":{"Exact Match Accuracy (Dev)":"73.1","Exact Match Accuracy (Test)":"70.1"},"uses_additional_data":false,"paper_date":"2021-11-01","paper":"/paper/sadga-structure-aware-dual-graph-aggregation","paper_url":"https://arxiv.org/abs/2111.00653v3","paper_title":"SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL","code":"https://github.com/dmirlab-group/sadga","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":14,"model":"RYANSQL (BERT)","metrics":{"Exact Match Accuracy (Dev)":"66.6","Exact Match Accuracy (Test)":"58.2"},"uses_additional_data":false,"paper_date":"2020-04-07","paper":"/paper/ryansql-recursively-applying-sketch-based","paper_url":"https://arxiv.org/abs/2004.03125v1","paper_title":"RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases","code":"https://github.com/kakaoenterprise/RYANSQL","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"datagpt-sql-7B + InvalidSQL-Feedback","metrics":{"Exact Match Accuracy (Dev)":"81.6","Execution Accuracy (Dev)":"87.2"},"uses_additional_data":true,"paper_date":"2024-09-24","paper":"/paper/datagpt-sql-7b-an-open-source-language-model-1","paper_url":"https://arxiv.org/abs/2409.15985v1","paper_title":"DataGpt-SQL-7B: An Open-Source Language Model for Text-to-SQL","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"datagpt-sql-7B","metrics":{"Exact Match Accuracy (Dev)":"80.3","Execution Accuracy (Dev)":"84.8"},"uses_additional_data":true,"paper_date":"2024-09-24","paper":"/paper/datagpt-sql-7b-an-open-source-language-model-1","paper_url":"https://arxiv.org/abs/2409.15985v1","paper_title":"DataGpt-SQL-7B: An Open-Source Language Model for Text-to-SQL","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"code-davinci-002 175B (LEVER)","metrics":{"Execution Accuracy (Dev)":"81.9"},"uses_additional_data":false,"paper_date":"2023-02-16","paper":"/paper/lever-learning-to-verify-language-to-code","paper_url":"https://arxiv.org/abs/2302.08468v3","paper_title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","code":"https://github.com/niansong1996/lever","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":16,"n_samples":22,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"DELLM + GPT-4","metrics":{"Execution Accuracy (Dev)":"71.68"},"uses_additional_data":false,"paper_date":"2024-02-18","paper":"/paper/knowledge-to-sql-enhancing-sql-generation","paper_url":"https://arxiv.org/abs/2402.11517v3","paper_title":"Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM","code":"https://github.com/Rcrossmeister/Knowledge-to-SQL","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"RATSQL + GAP","metrics":{"Exact Match Accuracy (Dev)":"71.8"},"uses_additional_data":false,"paper_date":"2020-12-18","paper":"/paper/learning-contextual-representations-for","paper_url":"https://arxiv.org/abs/2012.10309v1","paper_title":"Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training","code":"https://github.com/awslabs/gap-text2sql","n_code_links":3,"syntology":null},{"rank_in_archive_order":20,"model":"MAPO + TABERTLarge (K = 3)","metrics":{"Exact Match Accuracy (Dev)":"64.5"},"uses_additional_data":false,"paper_date":"2020-05-17","paper":"/paper/tabert-pretraining-for-joint-understanding-of","paper_url":"https://arxiv.org/abs/2005.08314v1","paper_title":"TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data","code":"https://github.com/facebookresearch/tabert","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":11,"rows_with_any_sample_ran":9,"distinct_papers_with_graph_line":11,"distinct_papers_with_any_sample_ran":9,"samples_over_distinct_papers":{"n_ran":36,"n_unverified":33,"n_samples":69,"n_pointer_only_licence":16,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":36,"n_unverified":33,"n_samples":69,"n_pointer_only_licence":16,"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"}}}