# Baidu open-sources Unlimited OCR 2 for parsing documents of any length

> Original title: Baidu Open-Sources Unlimited OCR 2, Parsing Documents of Any Length in One Pass

- Source: Pandaily
- Published: 2026-10-28T01:50:23.000Z
- Bad Influence: https://badinfluence.news/items/kfmrtgbnt93b9hn6zu290xa5s
- Original: https://pandaily.com/baidu-open-sources-unlimited-ocr-2-sr-swa-any-length-document-parsing-marathondocbench

## Summary

Baidu has released and open-sourced Unlimited OCR 2, a document parsing model meant to read documents of any page count in one pass. Its code and weights are on GitHub and Hugging Face under the MIT license, and the model is also offered through Baidu AI Cloud. Baidu reports 84.6 on MPDocBench and 77.1 on MarathonDocBench, figures that are its own tests and have not been independently evaluated.

## Why it matters

The article explains how the new attention design lets a document parser handle very long inputs, a method that may matter to developers working on large documents.