SoMark Team Open-Sources 1.3B Document Parsing Model OXR, Topping Three Benchmarks
English text is being prepared.
The SoMark team has open-sourced the document parsing model OXR. The main model has only 1.3B parameters and topped all three benchmark tests: OmniDocBench, olmOCR-Bench, and DocParsingBench. Its full parsing speed exceeds that of PaddleOCR-VL-1.6 and MinerU2.5-Pro, which were also tested in the same round. The model covers 13 types of document elements, including text, tables, formulas, chemical structure formulas, and code blocks. It can parse reading order and output layout coordinates, converting PDFs and document images into Markdown / JSON for downstream processes such as Agents and RAG.
Why read this
AI score 60
The original text provides the three benchmark top rankings and speed comparisons, allowing readers to judge where lightweight document parsing models fit in the RAG pipeline.
Topics
Body
文档解析赛道，又迎来一位强劲的新选手。
OXR 正式开源：主模型仅 1.3B 参数，在 OmniDocBench、olmOCR-Bench 和 DocParsingBench 三项基准测试中全部登顶，完整解析速度也超过了同场参测的 PaddleOCR-VL-1.6 和 MinerU2.5-Pro，把轻量模型的精度与效率同时推到了榜首。 其背后的 SoMark 团队来自国内一家初创公司，深耕于文档智能领域，此前持续围绕核心产品 SoMark 打磨解析能力，如今推出了开源模型 OXR。
多栏论文、报纸和试卷还考验阅读顺序。即便每个区域都识别正确，左右栏串读、正文与旁注混杂，仍会破坏原文含义。OXR 在识别内容的同时判断阅读顺序，并提供版面坐标，保留内容在页面中的位置。
这些能力共同构成了 OXR 的“Everything”：覆盖文字、表格、公式、化学结构式、代码块等 13 类文档元素，将 PDF 和文档图片解析为 Markdown / JSON，供 Agent、RAG 等下游流程使用。
本文由SoMark团队提供，量子位获授权转载，观点归原作者所有。