studio-dots-ai /dots.ocr

Multilingual Document Layout Parsing in a Single Vision-Language Model

★ 9,192⑂ 803👁 54⑃ 35● 253▤ 0
PythonMITCreated 2025-07-30
+0
日增长
9,192
stars
803
forks
54
watchers
35
prs
253
issues
0
releases

README

dots.ocr







  🖥️ Live Demo | 
  💬 WeChat | 
  📕 rednote | 
  🐦 X






 Introduction

dots.ocr Designed for universal accessibility, it possesses the capability to recognize virtually any human script. Beyond achieving state-of-the-art (SOTA) performance in standard multilingual document parsing among models of comparable size, dots.ocr-1.5 excels at converting structured graphics (e.g., charts and diagrams) directly into SVG code, parsing web screens and spotting scene text. 

 News 
 2026.03.19  We have rebranded dots.ocr-1.5 as dots.mocr. For technical details, please refer to our paper. The model weights are available on Hugging Face: dots.mocr and dots.mocr-svg.
 2025.10.31  🚀 We release dots.ocr.base, foundation VLM focus on OCR tasks, also the base model of dots.ocr. Try it out!
 2025.07.30  🚀 We release dots.ocr, — a multilingual documents parsing model based on 1.7b llm, with SOTA performance.




 Evaluation

 1. Document Parsing

 1.1 Elo Score of different bench between latest models


  
    
      models
      olmOCR-Bench
      OmniDocBench (v1.5)
      XDocParse
      Average
    
  
  
    
      MonkeyOCR-pro-3B
      895.0
      811.3
      637.1
      781.1
    
    
      GLM-OCR
      884.2
      972.6
      820.7
      892.5
    
    
      PaddleOCR-VL-1.5
      897.3
      997.9
      866.4
      920.5
    
    
      HuanyuanOCR
      997.6
      1003.9
      951.1
      984.2
    
    
      dots.ocr
      1041.1
      1027.2
      1190.3
      1086.2
    
    
    
      dots.mocr
      1104.4
      1059.0
      1210.7
      1124.7
    
    
      Gemini 3 Pro
      1180.4
      1128.0
      1323.7
      1210.7
    
  



 Notes: 
 - Results for Gemini 3 Pro, PaddleOCR-VL-1.5, and GLM-OCR were obtained via APIs, while HuanyuanOCR results were generated using local inference.
 - The Elo score evaluation was conducted using Gemini 3 Flash. The prompt can be found at: Elo Score Prompt. These results are consistent with the findings on ocrarena.


 1.2 olmOCR-bench

    
        
            Model
            ArXiv
            Old scans math
            Tables
            Old scans
            Headers & footers
            Multi column
            Long tiny text
            Base
            Overall
        
    
    
        
            Mistral OCR API
            77.2
            67.5
            60.6
            29.3
            93.6
            71.3
            77.1
            99.4
            72.0±1.1
        
        
            Marker 1.10.1
            83.8
            66.8
            72.9
            33.5
            86.6
            80.0
            85.7
            99.3
            76.1±1.1
        
        
            MinerU 2.5.4
            76.6
            54.6
            84.9
            33.7
            96.6
            78.2
            83.5
            93.7
            75.2±1.1
        
        
            DeepSeek-OCR
            77.2
            73.6
            80.2
            33.3
         

Top issues

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON