mineru

A developer benchmarks three PDF-parsing models (MinerU, Granite-Docling, PaddleOCR-VL) across six document types and twelve capabilities, finding MinerU drops footers unless its markdown is rebuilt while Granite-Docling outputs cleaner native markdown tables.

A comparison of on-prem document processing tools—Docling, Liteparse, Mineru, and Unstructured—for university use, evaluating their suitability for local deployment.

Recommending MinerU 3.1 document parsing tool, which perfectly converts PDF, Word, PPT etc. to Markdown, supports auto-identification of tables, formulas, images, and offers three modes (Pipeline/VLM), open-source and commercially usable.

MinerU is an open-source tool by OpenDataLab for extracting data from PDFs and documents.