Baidu Open-Sources and Releases ERNIE Unlimited OCR 2 Document Parsing Model, Supporting Unlimited Page Counts
English text is being prepared.
On the 27th of this month, Baidu officially released and open-sourced the ERNIE Unlimited OCR 2 document parsing model, pushing the document parsing limit from dozens of pages to "unlimited," and can parse all 7 works of the entire Harry Potter series, totaling more than 3,600 pages, in a single pass. The model natively supports layout element segmentation and recognition, and has cross-page text merging and table recognition merging capabilities. It scored 84.6 on MPDocBench and 77.1 on MarathonDocBench, achieving end-to-end performance SOTA on both.
Why read this
AI score 56
The original text provides the page limit, cross-page merging capability, and two benchmark scores, allowing readers to judge the progress in long-document parsing.
Topics
Body
百度开源发布文心 Unlimited OCR 2 文档解析模型，支持“无限”页数
2026-10-30 14:17 IT之家 - 溯波（实习）
IT之家 10 月 30 日消息，百度 (Baidu) 本月 27 日正式发布并开源文心 Unlimited OCR 2 模型。其将文档解析的上限从数十页推向“无限”，能一次性解析累计超过 3,600 页的《哈利 · 波特》全系列 7 部作品。
Unlimited OCR 2 原生支持版面要素切分识别，具备跨页文案合并、表格识别合并能力，在同样算力下处理更多、更快、更省。
百度表示，文心 Unlimited OCR 2 在面向多页文档解析的 MPDocBench 基准测试上得到 84.6 分、在专门评估百页级超长文档解析能力的 MarathonDocBench 基准测试上得到 77.1 分，均实现端到端性能 SOTA。
参考
广告声明：文内含有的对外跳转链接（包括不限于超链接、二维码、口令等形式），用于传递更多信息，节省甄选时间，结果仅供参考，IT之家包含外链的文章均包含本声明。