OpenDataLoader PDF: open-source parser tops benchmarks with 0.907 accuracy

mdancho84 · x · 2026-09-15

OpenDataLoader PDF is a new open-source parser for AI-ready data that has racked up 29k GitHub stars. It extracts Markdown, HTML, and JSON with bounding boxes from any PDF, handling complex layouts, tables, and nested structures. It runs fully local on CPU, with an AI-hybrid mode for tricky pages. On a benchmark of 200 real-world documents it scores 0.907 overall and 0.928 table accuracy, ranking #1. SDKs available for Python, Java, and Node, free and open source.

Related event: Open-Source PDF Parser OpenDataLoader Tops Benchmarks(2 posts)→

Original post →

More from coding & agent

coding & agent channel →