Baidu releases and open-sources Wenxin Unlimited OCR 2 for long document parsing
OCR 3.0 时代来了！文心 Unlimited OCR 2 开源发布，超长文档解析迎来“页数自由”
- Who
- Baidu
- What
- released and open-sourced Wenxin Unlimited OCR 2
- When
- Quote
10月27日，百度发布并开源文心 Unlimited OCR 2，全球首次实现任意页数文档解析，将 OCR 的处理上限从数十页推向“无限”，并达到最先进水平（SOTA）。
What happened
Baidu released and open-sourced Wenxin Unlimited OCR 2 on October 27, claiming document parsing without a page limit. The report cites scores of 84.6 on MPDocBench and 77.1 on MarathonDocBench, and says its SR-SWA attention mechanism delivers 7x faster single-step decoding than Full Attention on hundred-page documents. Code and model weights are available at https://github.com/baidu/Unlimited-OCR and https://huggingface.co/baidu/Unlimited-OCR-2.
Read next
See the full storyBaidu releases and open-sources Wenxin Unlimited OCR 2 for long-document parsingThe story so far
Baidu released and open-sourced Wenxin Unlimited OCR 2, making its code and model weights available on GitHub and Hugging Face while claiming it can parse documents without a page limit. The model is also available through Baidu AI Cloud and Baidu’s AI Open Platform for developers and enterprise users. Leiphone reported scores of 84.6 on MPDocBench and 77.1 on MarathonDocBench. It also reported that the model’s SR-SWA attention mechanism delivers seven times faster single-step decoding than Full Attention on hundred-page documents.
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue · 2026-10-27