# Baidu open-sources Unlimited OCR 2 document parsing model

> Original title: 刚刚，百度开源再拿全球第一！1000万下载神作杀回来了

- Source: AI Era
- Published: 2026-10-28T00:05:36.000Z
- Bad Influence: https://badinfluence.news/items/u8ui0alxsk0tvzbtzlzw8671i
- Original: https://aiera.com.cn/2026/10/28/other/admin/120974/%e5%88%9a%e5%88%9a%ef%bc%8c%e7%99%be%e5%ba%a6%e5%bc%80%e6%ba%90%e5%86%8d%e6%8b%bf%e5%85%a8%e7%90%83%e7%ac%ac%e4%b8%80%ef%bc%811000%e4%b8%87%e4%b8%8b%e8%bd%bd%e7%a5%9e%e4%bd%9c%e6%9d%80%e5%9b%9e/

## Summary

Baidu has open-sourced Wenxin Unlimited OCR 2, a new-generation document parsing model, four months after its predecessor. The source text provided does not give benchmark scores, parameter counts, or pricing.