MinerU

Open-source document parser that turns PDFs, Office files and images into Markdown or JSON; also a desktop client and web app.

Where it ranks

S
Documents & OCR
Parsers & APIs · Local · via MinerU2.5-Pro-2605-1.2B
With cloud models: tier S (86 on OmniDocBench v1.6 (end-to-end, v1.6_full): pipeline tools)

Ranked by its own benchmark result where it has one; otherwise by the best model it offers.

Vendor: OpenDataLab (Shanghai AI Laboratory)
Approach: Parsers & APIs
Where it runs: Runs fully on your hardware with local models; cloud models optional
Interface: Command line, API, Desktop app, Web app
Skill level: Intermediate: some setup or configuration
Price: Free, open source
Pricing notes: Open-source toolkit free; online web app, desktop client and API at mineru.net (pricing not verified).
Source code: Open source (MinerU Open Source License (Apache-2.0 with additional terms))
GitHub stars: 82k (18 Oct 2026)
Last verified: 18 Oct 2026

Price from github.com, 18 Oct 2026.

Benchmark	Result	Entry on the leaderboard	As of	Source
OmniDocBench v1.6 (end-to-end, v1.6_full): pipeline tools	86	`MinerU-Pipeline` Pipeline-tools row of the OmniDocBench v1.6_full end-to-end table, evaluated at MinerU 3.4.0; the VLM backend's model is tracked as model 'mineru'.	11 Sep 2026	github.com