Open-Source Tool Marker Converts PDFs and Documents to Markdown with Industry-Leading Speed and Accuracy
Summary
Marker, a powerful open-source conversion tool, transforms PDFs, DOCX, XLSX, and more into markdown or JSON at industry-leading speeds of up to 23.7 pages per second, outperforming rivals MinerU and docling with a 76% accuracy benchmark score while supporting optional AI integration via Gemini, Claude, and OpenAI.
Key Points
- Marker is an open-source tool that converts PDFs, images, PPTX, DOCX, XLSX, HTML, and EPUB files into markdown, JSON, HTML, or chunks with high accuracy, supporting tables, equations, code blocks, and multi-language documents.
- Benchmarks on olmocr-bench show Marker's balanced mode scoring 76.0% overall and 83.5% on born-digital PDFs, outperforming MinerU and docling on both accuracy and throughput, achieving 2.9 pages per second in balanced mode and up to 23.7 pages per second in fast no-OCR mode on a single B200 GPU.
- Marker supports optional LLM integration via Gemini, Claude, OpenAI, Azure, and others to boost accuracy for complex documents, and is installable via pip with a Python API, CLI, interactive Streamlit app, and a FastAPI server for small-scale deployments.