Papers › Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database...

Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs

4 May 2023NeurIPS 2023 11arXiv:2305.03111archive 2025-07-28

Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Rongyu Cao, Ruiying Geng, Nan Huo, Xuanhe Zhou, Chenhao Ma, Guoliang Li, Kevin C. C. Chang, Fei Huang, Reynold Cheng, Yongbin Li

Text-to-SQL parsing, which aims at converting natural language instructions into executable SQLs, has gained increasing attention in recent years. In particular, Codex and ChatGPT have shown impressive results in this task. However, most of the prevalent benchmarks, i.e., Spider, and WikiSQL, focus on database schema with few rows of database contents leaving the gap between academic study and real-world applications. To mitigate this gap, we present Bird, a big benchmark for large-scale database grounded in text-to-SQL tasks, containing 12,751 pairs of text-to-SQL data and 95 databases with a total size of 33.4 GB, spanning 37 professional domains. Our emphasis on database values highlights the new challenges of dirty database contents, external knowledge between NL questions and database contents, and SQL efficiency, particularly in the context of massive databases. To solve these problems, text-to-SQL models must feature database value comprehension in addition to semantic parsing. The experimental results demonstrate the significance of database values in generating accurate text-to-SQLs for big databases. Furthermore, even the most effective text-to-SQL models, i.e. ChatGPT, only achieves 40.08% in execution accuracy, which is still far from the human result of 92.96%, proving that challenges still stand. Besides, we also provide an efficiency analysis to offer insights into generating text-to-efficient-SQLs that are beneficial to industries. We believe that BIRD will contribute to advancing real-world applications of text-to-SQL research. The leaderboard and source code are available: https://bird-bench.github.io/.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 6 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 6 samples from 1 repository, 6 ran (0 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

bird-bench/mini_dev mentioned on GitHubSyntology: 6 samples, 6 ran (6 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong

Licence: 6 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from bird-bench/mini_dev. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

bird-bench/mini_dev community (archive-listed) 6 samples, 6 ran (6 instrument-failed) · 0 unverified
connect_gpt llm/src/gpt_request.py ran · our draft was wrong no licence file found · pointer only · fc5d13ba31f06eec · report fixture: signature engine:str/0/str, prompt:str/0/str, max_tokens:int/0/int, temperature:float/0/float, stop:list/1/str, client:MockClient/0/? · returned str · level recorded 2026-09-22
decouple_question_schema llm/src/gpt_request.py ran · our draft was wrong no licence file found · pointer only · 5076b6aec7f58d64 · report fixture: signature datasets:list/1/dict, db_root_path:str/0/str · returned tuple · level recorded 2026-09-22
generate_sql_file llm/src/gpt_request.py ran · our draft was wrong no licence file found · pointer only · 545a130b9f353336 · report fixture: signature sql_lst:list/1/tuple, output_path:str/0/str · returned dict · level recorded 2026-09-22
get_connection_for_phase live_sql_bench_sqlite/evaluation/db_utils.py ran · our draft was wrong no licence file found · pointer only · 8f7f721f16a15911 · report fixture: signature db_path:str/0/str, logger:MockLogger/0/? · returned Connection · level recorded 2026-09-22
perform_query_on_sqlite_databases live_sql_bench_sqlite/evaluation/db_utils.py ran · our draft was wrong no licence file found · pointer only · 85f2b26606b1f79e · report fixture: signature query:str/0/str, db_path:str/0/str, conn:NoneType/0/?, query_timeout:int/0/int · returned tuple · level recorded 2026-09-22
sql_response_extract finetuning/inference/vllm_infer.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a7e85c53a98d5fc1 · report fixture: signature response_string:str/0/str · returned str · level recorded 2026-09-22

Tasks

SQL ParsingSemantic ParsingText to SQLText-To-SQL

Datasets

Introduced by this paper, per the archive.

BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) CoT + ChatGPT Execution Accuracy % (Dev) 36.64 #34 of 41 Archive leaderboard report
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) CoT + ChatGPT Execution Accuracy % (Test) 40.08 #34 of 41 Archive leaderboard report
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) ChatGPT (Baseline) Execution Accuracy % (Dev) 37.22 #35 of 41 Archive leaderboard report
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) ChatGPT (Baseline) Execution Accuracy % (Test) 39.30 #35 of 41 Archive leaderboard report
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) Codex (Baseline) Execution Accuracy % (Dev) 34.35 #36 of 41 Archive leaderboard report
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) Codex (Baseline) Execution Accuracy % (Test) 36.47 #36 of 41 Archive leaderboard report
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) Palm-2 (Baseline) Execution Accuracy % (Dev) 27.38 #37 of 41 Archive leaderboard report
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) Palm-2 (Baseline) Execution Accuracy % (Test) 33.04 #37 of 41 Archive leaderboard report
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) Human Performance Execution Accurarcy (Human) 92.96 #41 of 41 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections