datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
SQL-Queries-DatasetSQL-Queries-Datasetbird-sqlecommerce-analytics-sql-evaluation
Ecommerce Analytics SQL Evaluation (declared GMV, verified answer key)
An evalpack: an evaluation database generated from the answer key, not
annotated after the fact. A VLDB 2026 audit found 52.8% of BIRD Mini-Dev
answer keys wrong because benchmarks annotate answers onto existing
databases; this dataset inverts the order. The declared properties (curves,
shares, identities) are the specification, the database is generated to
satisfy them exactly, and every shipped question was… See the full description on the dataset page: https://huggingface.co/datasets/rasinmuhammed/ecommerce-analytics-sql-evaluation.saas-finance-sql-evaluation
SaaS Finance SQL Evaluation (MRR waterfalls that reconcile exactly)
An evalpack: an evaluation database generated from the answer key, not
annotated after the fact. A VLDB 2026 audit found 52.8% of BIRD Mini-Dev
answer keys wrong because benchmarks annotate answers onto existing
databases; this dataset inverts the order. The declared properties (curves,
shares, identities) are the specification, the database is generated to
satisfy them exactly, and every shipped question was… See the full description on the dataset page: https://huggingface.co/datasets/rasinmuhammed/saas-finance-sql-evaluation.spider-sql-promptssql-spider-kaggledbqa-with-contextedtech-sql-evaluation
EdTech SQL Evaluation (declared learning curve, verified answer key)
An evalpack: an evaluation database generated from the answer key, not
annotated after the fact. A VLDB 2026 audit found 52.8% of BIRD Mini-Dev
answer keys wrong because benchmarks annotate answers onto existing
databases; this dataset inverts the order. The declared properties (curves,
shares, identities) are the specification, the database is generated to
satisfy them exactly, and every shipped question was… See the full description on the dataset page: https://huggingface.co/datasets/rasinmuhammed/edtech-sql-evaluation.synthetic_sql_queries_samplebird_text_to_sqlLLM_SQL_BaseDatosEspanol
Usos
Usos directos
El objetivo principal de este dataset es proporcionar ejemplos simples para el fine-tuning de modelos
de procesamiento de lenguaje natural (NLP) en el contexto de consultas SQL.
Usos fuera de mira
Podria usarse para el entrenamiento de una IA que sirva como creadora de base de datos artificiales
Estructura del conjunto de datos
Question: Es la pegunta que el usuario le dara al chatbot
Answer: La respuesta el que chatbot le… See the full description on the dataset page: https://huggingface.co/datasets/somosnlp/LLM_SQL_BaseDatosEspanol.bird_nl_to_sql_nodeautotrain-data-nl-to-sqlsql-urlshape-quote-0910
Controlled SQL URL shape probe
pg-wikiSQL-sql-instructions-80kConverted, cleaned and syntax-checked SQLWiki dataset.
The datapoints containing non latin column names were removed.
Resulting SQL statements were adapted for Postgres syntax and conventions.
Each SQL statement, including CREATE TABLE statements were syntax checked with pgsanity.
Citations
@article{zhongSeq2SQL2017,
author = {Victor Zhong and
Caiming Xiong and
Richard Socher},
title = {Seq2SQL: Generating Structured Queries from Natural… See the full description on the dataset page: https://huggingface.co/datasets/kaxap/pg-wikiSQL-sql-instructions-80k.query_builder_text_to_sqlsqlconsole-victimsynthetic_text_to_sql_th
Synthetic Text-to-SQL Thai Dataset
Thai translation of the gretelai/synthetic_text_to_sql dataset.
Dataset Description
This dataset contains Thai translations of synthetic text-to-SQL examples covering various domains and SQL patterns.
Source
Original Dataset: gretelai/synthetic_text_to_sql
Created by: Gretel.ai
Statistics
Split
Rows
Train
100,000
Test
5,851
Total
105,851
Columns
Column
Description… See the full description on the dataset page: https://huggingface.co/datasets/Porameht/synthetic_text_to_sql_th.SQLShield
SQLShield
Dataset Summary
SQLShield is a dataset designed for training and evaluating models on detecting vulnerable versus benign SQL usage in natural language-driven database interfaces. It includes a rich collection of natural language questions, their corresponding SQL queries, relevant table contexts, and a binary vulnerability label indicating whether the SQL query is potentially malicious (1) or safe (0).
This dataset enables research to improve safety in… See the full description on the dataset page: https://huggingface.co/datasets/salmane11/SQLShield.sql_generator_no_cotsql-embed-authz-20260915Synthetic authorized SQL embed test fixture.
sql_injectionsql-dataLargehp_sqlMycoBase-Large-Scale-Text-to-SQL
MycoBase: A Biologically Literate Text-to-SQL Dataset
MycoBase is a synthetic but biologically accurate dataset designed for stress-testing Text-to-SQL systems. It represents a research information system for the study of fungi, covering everything from taxonomy and genomics to morphology and cultivation.
Dataset Highlights
Schema Complexity: 2,016 tables with over 9,000 foreign key relationships.
Data Volume: 320,270 rows of realistic mycology data.
Realistic Names:… See the full description on the dataset page: https://huggingface.co/datasets/FatimahEmadEldin/MycoBase-Large-Scale-Text-to-SQL.SQLQueryCodeDatasetvts-sqltext-to-sqlThis dataset is a merged collection of multiple text-to-SQL datasets, designed to provide a comprehensive resource for training and evaluating text-to-SQL models. It combines data from several popular benchmarks, including Spider, CoSQL, SparC, and others, to create a diverse and robust dataset for natural language to SQL query generation tasks.
Dataset Details
Dataset Description
Curated by: Mudasir Ahmad Mir
Language(s) (NLP): English
License: Apache 2.0
This dataset is ideal for researchers… See the full description on the dataset page: https://huggingface.co/datasets/Mudasir692/text-to-sql.sql-create-context-llama2-78kThis is dataset contain (78k samples) of the excellent b-mc2/sql-create-context and changed to derekiya/sql-create-context-llama2-78k dataset,
processed to match Llama 2's prompt format as described in this article.
Useful if you don't want to reformat it by yourself (e.g., using a script). It was designed for this article about fine-tuning a Llama 2 (chat)
o3_sql_agent_datasetSynthetic Dataset generated with o3 model.
Source Input: Chinook.db file, the popular example used in many LangChain tutorials
import sqlite3
import requests
from langchain_community.utilities.sql_database import SQLDatabase
from sqlalchemy import create_engine
from sqlalchemy.pool import StaticPool
def get_engine_for_chinook_db():
"""Pull sql file, populate in-memory database, and create engine."""
url =… See the full description on the dataset page: https://huggingface.co/datasets/asvs/o3_sql_agent_dataset.