Compare software

PaddleOCR vs MinerU: catalog facts
PaddleOCR	MinerU
Free Free and open source under the Apache licence.	Free Free to download and run; the repository does not declare a standard license.
Windows, macOS, Linux, Command line	Self-hosted, Command line
Parses layout, tables and formulas, not just lines of text Outputs JSON and Markdown ready for downstream processing	Parses tables, formulas and scanned pages with OCR Accepts PDF, Office, OpenDocument, EPUB, HTML and more
Built on the PaddlePaddle framework, which is a large dependency Much of the documentation and community is in Chinese	Setup and model downloads suit technical users Higher-quality parsing tiers need more compute
Downloadable app	Downloadable app, Self-hosted
Open source	Closed source
License: Apache-2.0	License not stated
Not stated if an account is needed	No account needed
Not stated if it works offline	Works offline
Official website Full listing and sources Checked September 22, 2026	Official website Full listing and sources Checked September 23, 2026

Catalog facts only. Anything “not stated” is unconfirmed. Check full listings for details.