# Baidu open-sources Unlimited OCR 2 for hundred-page document parsing

> Original title: Baidu Open-Sources Unlimited OCR 2 for Hundred-Page Document Parsing

- Source: MarkTechPost
- Published: 2026-10-27T05:26:36.000Z
- Bad Influence: https://badinfluence.news/items/s2mm2zn56rt0nybfhvl813acz
- Original: https://www.marktechpost.com/2026/10/26/baidu-unlimited-ocr-2-open-source-long-document-ocr/

## Summary

Baidu has released Unlimited OCR 2, a 3.34B-parameter open-source OCR model under the MIT license that parses documents of hundreds of pages in one request. Its SR-SWA sparse attention caps attention at a fixed 512-token reference set, and Baidu reports 77.1 on MarathonDocBench against 33.7 for the next model. All benchmark figures are self-reported, and heading hierarchy is the weakest sub-score at 48.2.