studio-dots-ai /dots.ocr
Multilingual Document Layout Parsing in a Single Vision-Language Model
★ 9,192⑂ 803👁 54⑃ 35● 253▤ 0
+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
#31Requires Flash-Attention version >=2.7.1,<=2.7.4 but got 2.8.0.post2.18 comments · 2025-08-05#56How to finetune dot.ocr16 comments · 2025-08-07#175vllm 0.9.1版本不兼容flash-attn==2.8.0.post2版本,启动的时候报错15 comments · 2025-09-04#74请问可否支持NPU 910B以及规划15 comments · 2025-08-11#85flash-attn依赖冲突13 comments · 2025-08-12#46TypeError: Received a NoneType for argument video_processor, but a BaseVideoProcessor was expected. #Help me to fix this issue11 comments · 2025-08-06#78Using with Tesla T4 GPU9 comments · 2025-08-11#49解析结果陷入重复死循环9 comments · 2025-08-07