illuin-tech/vidore-benchmark

Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.

63
/ 100
Established

This tool helps researchers and practitioners evaluate how well their end-to-end visual document retrieval systems perform. You provide your document retrieval pipeline and it runs against various document types like HR, finance, or industrial documents. The output is a set of performance metrics and computing times, allowing you to compare your pipeline against others on a public leaderboard.

265 stars. Available on PyPI.

Use this if you are developing a system that needs to find specific information within a large collection of visual documents and want to rigorously measure its effectiveness and efficiency.

Not ideal if you are only evaluating individual model components, rather than a full, multi-stage document retrieval system.

document-retrieval information-extraction machine-learning-evaluation optical-character-recognition information-systems
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

265

Forks

35

Language

Python

License

MIT

Last pushed

Feb 27, 2026

Commits (30d)

0

Dependencies

10

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/illuin-tech/vidore-benchmark"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.