Xiaomi Open-Sources 0.8B Document Understanding Model Xiaomi-OCR-0
English text is being prepared.
Xiaomi has released and open-sourced a lightweight document understanding model, Xiaomi-OCR-0, with only 0.8B parameters, integrating three capabilities—document parsing, key information extraction, and OCR visual question answering—into one. The model scored 95.24 on Real5-OmniDocBench, ranking first among compared models, and scored 96.83 on OmniDocBench v1.6, ranking first among models under 1B parameters, with an average score of 83.2 across five mainstream OCR visual question answering benchmarks. Xiaomi has also open-sourced the model weights and inference code, and provides a Demo, MCP service, and Agent Skill toolkit. The related technology has already been used in Xiaomi phones and "Super Xiao Ai" for screen information recognition such as pickup codes, bills, and cards.
Why read this
AI score 63
Xiaomi has open-sourced a 0.8B document understanding model, providing multiple benchmark scores and on-device smartphone deployment scenarios, allowing comparison of the parameter-efficiency ratio of lightweight models on OCR tasks.
Topics
Body
小米开源0.8B“卷王”OCR模型：8亿参数，越级挑战大模型凤凰网科技下载客户端 独家抢先看2026年10月31日 11:51:57 来自北京市Updated 2026年10月31日 11:52:28
凤凰网科技讯（作者/于雷）10月31日，小米昨日发布并开源轻量级文档理解模型Xiaomi-OCR-0。该模型仅0.8B参数，将文档解析、关键信息抽取与OCR视觉问答三类能力合为一体，主打在轻量级体量下实现复杂文档的结构化解析与语义理解。
从评测表现看，Xiaomi-OCR-0在真实拍摄干扰场景的Real5-OmniDocBench上取得95.24分，位列对比模型第一。
在OmniDocBench v1.6上取得96.83分，以0.8B参数夺得总榜第二、1B以下模型第一。
在五项主流OCR视觉问答基准上，其平均分为83.2，超过部分专用OCR模型和更大尺寸通用多模态模型，展示出较高的参数效能比。
技术层面，小米称该模型基于约1.7亿条高质量样本训练，核心在于可扩展数据引擎与“先解析、后理解”的渐进式训练策略，以降低伪标签噪声并补足复杂版式和长尾场景能力。
落地方面，相关技术已进入小米手机与“超级小爱”场景，可用于取餐码、账单、卡证、日程和航班信息等屏幕信息的识别与后续操作。小米同时开源模型权重与推理代码，并提供Demo、MCP服务及Agent Skill工具包，面向开发者开放集成。