SoMark 开源 1.3B 文档解析模型 OXR，登顶 olmOCR-Bench 等三榜

Rohan Paul· @rohanpaul_ai · X·2026-10-21 03:39· 1 小时前AI 评分54

AI 导读

SoMark 团队发布开源文档解析模型 OXR（1.3B 参数），将 PDF 和文档图像转为含布局坐标的 Markdown 或 JSON 的 Agent-Friendly 数据。

正文 · 原文

OXR makes parsing failures part of the training process.

During post-training (OXR is the first document parser to use RSI here), a VLM evaluates its outputs, rollout disagreements flag uncertainty, and a separate clustering model groups the causes;

those findings then guide targeted data generation for the next round, and the 1.3B model that comes out of it sits first on olmOCR-Bench, OmniDocBench and DocParsingBench while running 3.05× GLM-OCR's throughput on a single RTX PRO 6000, the fastest open-source result in the speed comparison.

Worth studying (Github link in comment)

来源：Rohan Paul · x.com