RRepoGEO

REPOGEO REPORT · LITE

defog-ai/sql-eval

Default branch main · commit b8333241 · scanned 6/3/2026, 2:32:58 PM

GitHub: 744 stars · 72 forks

AI VISIBILITY SCORE
35 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface defog-ai/sql-eval, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • hightopics#1
    Add relevant topics for Text-to-SQL evaluation

    Why:

    COPY-PASTE FIX
    llm, text-to-sql, sql-evaluation, nlp, generative-ai, benchmarking, data-science, machine-learning, ai-models
  • highreadme#2
    Reposition README H1/intro to clearly state its purpose as a Text-to-SQL evaluation framework

    Why:

    CURRENT
    # SQL Generation Evaluation

This repository contains the code that Defog uses for the evaluation of generated SQL. It's based off the schema from the Spider, but with a new set of hand-selected questions and queries grouped by query category. For an in-depth look into our process of creating this evaluation approach, see this.
    COPY-PASTE FIX
    # SQL Generation Evaluation: A Semantic Benchmarking Framework for LLM-Generated SQL

This repository provides Defog's robust framework for semantically evaluating the accuracy of SQL queries generated by Large Language Models (LLMs). Unlike tools that only parse or generate SQL, `sql-eval` focuses on comparing the *results* of generated SQL against gold-standard queries, ensuring true correctness. It's based on the Spider schema, enhanced with hand-selected questions and queries grouped by category.
  • mediumhomepage#3
    Add a homepage URL to the Defog AI website

    Why:

    COPY-PASTE FIX
    https://defog.ai

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface defog-ai/sql-eval
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
sqlflow-dev/sqlflow
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. sqlflow-dev/sqlflow · recommended 1×
  2. tobymao/sqlglot · recommended 1×
  3. psycopg/psycopg2 · recommended 1×
  4. mysql/mysql-connector-python · recommended 1×
  5. sqlite3 · recommended 1×
  • CATEGORY QUERY
    How can I measure the correctness of SQL queries produced by large language models?
    you: not recommended
    AI recommended (in order):
    1. SQLFlow (sqlflow-dev/sqlflow)
    2. SQLGlot (tobymao/sqlglot)
    3. psycopg2 (psycopg/psycopg2)
    4. mysql-connector-python (mysql/mysql-connector-python)
    5. sqlite3
    6. pandas (pandas-dev/pandas)
    7. sqlfluff (sqlfluff/sqlfluff)
    8. pgFormatter (darold/pgFormatter)
    9. PyTest (pytest-dev/pytest)

    AI recommended 9 alternatives but never named defog-ai/sql-eval. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What tools are available for benchmarking the accuracy of text-to-SQL models?
    you: not recommended
    AI recommended (in order):
    1. Spider Dataset (https://github.com/taoyds/spider)
    2. WikiSQL Dataset (https://github.com/salesforce/WikiSQL)
    3. Hugging Face `evaluate` library (https://github.com/huggingface/evaluate)
    4. SQLFlow (https://github.com/sql-flow/sqlflow)
    5. `cx_Oracle` (https://github.com/oracle/python-cx_Oracle)
    6. `pyodbc` (https://github.com/mkleehammer/pyodbc)

    AI recommended 6 alternatives but never named defog-ai/sql-eval. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    warn

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of defog-ai/sql-eval?
    pass
    AI named defog-ai/sql-eval explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts defog-ai/sql-eval in production, what risks or prerequisites should they evaluate first?
    pass
    AI named defog-ai/sql-eval explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo defog-ai/sql-eval solve, and who is the primary audience?
    pass
    AI named defog-ai/sql-eval explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of defog-ai/sql-eval. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/defog-ai/sql-eval.svg)](https://repogeo.com/en/r/defog-ai/sql-eval)
HTML
<a href="https://repogeo.com/en/r/defog-ai/sql-eval"><img src="https://repogeo.com/badge/defog-ai/sql-eval.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

defog-ai/sql-eval — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite