Datalab Marker v2 vs MinerU, Docling, and Liteparse: Benchmark Breakdown
Datalab has released Marker 2, an open-source document conversion pipeline that significantly outperforms competitors like MinerU and Docling in speed and accuracy. The update introduces device-aware modes and architectural changes to improve throughput for processing various document formats into structured data.
Datalab has released Marker 2 , a full rewrite of its open source document conversion pipeline. Marker converts PDF, image, PPTX, DOCX, XLSX, HTML, and EPUB files into markdown, JSON, HTML, or chunks. The Datalab team rebuilt it around three components shipped over the preceding months: Surya OCR 2 , a 20M-param fast layout model , and a rebuilt pdftext that is 3× faster than the previous one.
Get the full story
Sign up for Headlinne to unlock AI insights, political bias analysis, and your personalized news feed.
Create free accountAlready have an account? Sign in