WiNGPT-DocLoom-lite

<a href="https://wingpt.winning.com.cn/platform" target="_blank" style="margin: 2px;"> <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20WiNGPT-Platform%20-536af5" style="display: inline-block; vertical-align: middle;"/></a>

DocLoom-lite

<table> <tr> <td><img src="assets/9b5dd6de-1745-4062-911a-c2f838b2830b.png"></td> </tr> </table>

Benchmark Performance （olmOCR-Bench）

<!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>OCR Model Performance Table</title> </head> <body> <table> <thead> <tr> <th style="text-align: center;"></th> <th style="text-align: center;"></th> <th style="text-align: center;">Arxiv</th> <th style="text-align: center;">Old scans math</th> <th style="text-align: center;">Tables</th> <th style="text-align: center;">Old scans</th> <th style="text-align: center;">Headers and footers</th> <th style="text-align: center;">Multi columnn</th> <th style="text-align: center;">Long tiny text</th> <th style="text-align: center;">Base</th> <th style="text-align: center;">Overall</th> </tr> </thead> <tbody> <tr> <td style="text-align: center;">Marker 1.10.1</td> <td style="text-align: center;">--</td> <td style="text-align: center;">83.8</td> <td style="text-align: center;">66.8</td> <td style="text-align: center;">72.9</td> <td style="text-align: center;">33.5</td> <td style="text-align: center;">86.6</td> <td style="text-align: center;">80</td> <td style="text-align: center;">85.7</td> <td style="text-align: center;">99.3</td> <td style="text-align: center;">76.1±1.1</td> </tr> <tr> <td style="text-align: center;">MinerU 2.5.4</td> <td style="text-align: center;">--</td> <td style="text-align: center;">76.6</td> <td style="text-align: center;">54.6</td> <td style="text-align: center;">84.9</td> <td style="text-align: center;">33.7</td> <td style="text-align: center;">96.6</td> <td style="text-align: center;">78.2</td> <td style="text-align: center;">83.5</td> <td style="text-align: center;">93.7</td> <td style="text-align: center;">75.2±1.1</td> </tr> <tr> <td style="text-align: center;">DeepSeek-OCR</td> <td style="text-align: center;">--</td> <td style="text-align: center;">77.2</td> <td style="text-align: center;">73.6</td> <td style="text-align: center;">80.2 </td> <td style="text-align: center;">33.3 </td> <td style="text-align: center;">96.1 </td> <td style="text-align: center;">66.4 </td> <td style="text-align: center;">79.4 </td> <td style="text-align: center;">99.8 </td> <td style="text-align: center;">75.7±1.0 </td> </tr> <tr> <td style="text-align: center;">Nanonts-OCR2-3B</td> <td style="text-align: center;">3B</td> <td style="text-align: center;">75.4 </td> <td style="text-align: center;">46.1 </td> <td style="text-align: center;">86.8 </td> <td style="text-align: center;">40.9 </td> <td style="text-align: center;">32.1 </td> <td style="text-align: center;">81.9 </td> <td style="text-align: center;">93 </td> <td style="text-align: center;">99.6 </td> <td style="text-align: center;">69.5±1.1 </td> </tr> <tr> <td style="text-align: center;">Mistral OCR</td> <td style="text-align: center;">--</td> <td style="text-align: center;">77.2 </td> <td style="text-align: center;">67.5 </td> <td style="text-align: center;">60.6 </td> <td style="text-align: center;">29.3 </td> <td style="text-align: center;">93.6 </td> <td style="text-align: center;">71.3 </td> <td style="text-align: center;">77.1 </td> <td style="text-align: center;">99.4 </td> <td style="text-align: center;">72.0±1.1 </td> </tr> <tr> <td style="text-align: center;">MonkeyOCR-pro-3B</td> <td style="text-align: center;">3B</td> <td style="text-align: center;">83.8 </td> <td style="text-align: center;">68.8 </td> <td style="text-align: center;">74.6 </td> <td style="text-align: center;">36.1 </td> <td style="text-align: center;">91.2 </td> <td style="text-align: center;">76.6 </td> <td style="text-align: center;">80.1 </td> <td style="text-align: center;">95.3 </td> <td style="text-align: center;">75.8±1.0 </td> </tr> <tr> <td style="text-align: center;">Qwen3-VL-4B-Instruct</td> <td style="text-align: center;">4B</td> <td style="text-align: center;">83.1 </td> <td style="text-align: center;">74.5 </td> <td style="text-align: center;">83.9 </td> <td style="text-align: center;">40.5 </td> <td style="text-align: center;">35.5 </td> <td style="text-align: center;">81.7 </td> <td style="text-align: center;">88.7 </td> <td style="text-align: center;">99.3 </td> <td style="text-align: center;">73.4±1.0 </td> </tr> <tr> <td style="text-align: center;">olmOCR pipeline v0.4.0 with olmOCR-2-7B-1025</td> <td style="text-align: center;">7B</td> <td style="text-align: center;">82.9 </td> <td style="text-align: center;">82.1 </td> <td style="text-align: center;">84.3 </td> <td style="text-align: center;">48.3 </td> <td style="text-align: center;">95.7 </td> <td style="text-align: center;">84.3 </td> <td style="text-align: center;">81.4 </td> <td style="text-align: center;">99.7 </td> <td style="text-align: center;">82.3±1.1 </td> </tr> <tr> <td style="text-align: center;">Qwen3-VL-2B-Instruct</td> <td style="text-align: center;">2B</td> <td style="text-align: center;">66.7 </td> <td style="text-align: center;">50.9 </td> <td style="text-align: center;">66.6</td> <td style="text-align: center;">36.3 </td> <td style="text-align: center;">48 </td> <td style="text-align: center;">63.2 </td> <td style="text-align: center;">73.5 </td> <td style="text-align: center;">98.9 </td> <td style="text-align: center;">63.0±1.2 </td> </tr> <tr> <td style="text-align: center;">Qwen3.5-0.8B</td> <td style="text-align: center;">0.8B</td> <td style="text-align: center;">46.4</td> <td style="text-align: center;">32.5</td> <td style="text-align: center;">39.8</td> <td style="text-align: center;">32.5</td> <td style="text-align: center;">67.6</td> <td style="text-align: center;">29.6</td> <td style="text-align: center;">41</td> <td style="text-align: center;">92</td> <td style="text-align: center;">46.6±1.1</td> </tr> <tr> <td style="text-align: center;">Qwen3.5-2B</td> <td style="text-align: center;">2B</td> <td style="text-align: center;">65.8</td> <td style="text-align: center;">59</td> <td style="text-align: center;">62</td> <td style="text-align: center;">33.5</td> <td style="text-align: center;">65</td> <td style="text-align: center;">53.3</td> <td style="text-align: center;">65.6</td> <td style="text-align: center;">90.8</td> <td style="text-align: center;">61.9±1.2</td> </tr> <tr> <td style="text-align: center;">Qwen3.5-4B</td> <td style="text-align: center;">4B</td> <td style="text-align: center;">76.7</td> <td style="text-align: center;">83.6</td> <td style="text-align: center;">78.2</td> <td style="text-align: center;">42.6</td> <td style="text-align: center;">30.8</td> <td style="text-align: center;">76.5</td> <td style="text-align: center;">85.3</td> <td style="text-align: center;">91.3</td> <td style="text-align: center;">70.6±1.0</td> </tr> <tr> <td style="text-align: center;">FireRed-OCR-2B</td> <td style="text-align: center;">2B</td> <td style="text-align: center;">81.5</td> <td style="text-align: center;">75.1</td> <td style="text-align: center;">84.1</td> <td style="text-align: center;">33.5</td> <td style="text-align: center;">26.8</td> <td style="text-align: center;">78.6</td> <td style="text-align: center;">84.8</td> <td style="text-align: center;">97.3</td> <td style="text-align: center;">70.2±1.0</td> </tr> <tr> <td style="text-align: center;">Logics-Parsing-v2-4B</td> <td style="text-align: center;">4B</td> <td style="text-align: center;">79.7</td> <td style="text-align: center;">80.3</td> <td style="text-align: center;">85.6</td> <td style="text-align: center;">37.6</td> <td style="text-align: center;">89.6</td> <td style="text-align: center;">74.5</td> <td style="text-align: center;">91.2</td> <td style="text-align: center;">98.9</td> <td style="text-align: center;">79.7±1.0</td> </tr> <tr> <td style="text-align: center;">LightOnOCR-2-1B</td> <td style="text-align: center;">1B</td> <td style="text-align: center;">90.6</td> <td style="text-align: center;">83.8</td> <td style="text-align: center;">88.4</td> <td style="text-align: center;">42.6</td> <td style="text-align: center;">19.6</td> <td style="text-align: center;">85.1</td> <td style="text-align: center;">90</td> <td style="text-align: center;">99.6</td> <td style="text-align: center;">75.0±1.0</td> </tr> <tr> <td style="text-align: center;">GLM-OCR-0.9B</td> <td style="text-align: center;">0.9B</td> <td style="text-align: center;">75.8</td> <td style="text-align: center;">57.6</td> <td style="text-align: center;">43.3</td> <td style="text-align: center;">28.7</td> <td style="text-align: center;">83.9</td> <td style="text-align: center;">69.5</td> <td style="text-align: center;">52.5</td> <td style="text-align: center;">90</td> <td style="text-align: center;">67.2±1.1</td> </tr> <tr> <td style="text-align: center;">DocLoom (2025-12-31)</td> <td style="text-align: center;">4B</td> <td style="text-align: center;">74.3 </td> <td style="text-align: center;">66.6 </td> <td style="text-align: center;">80.9 </td> <td style="text-align: center;">45.1 </td> <td style="text-align: center;">91.4 </td> <td style="text-align: center;">82.9 </td> <td style="text-align: center;">89.1 </td> <td style="text-align: center;">99.7 </td> <td style="text-align: center;">78.8±1.0 </td> </tr> <tr> <td style="text-align: center;">DocLoom-lite</td> <td style="text-align: center;">2B</td> <td style="text-align: center;">71.4</td> <td style="text-align: center;">69.4</td> <td style="text-align: center;">75</td> <td style="text-align: center;">45.2</td> <td style="text-align: center;">90.4</td> <td style="text-align: center;">79.6</td> <td style="text-align: center;">91</td> <td style="text-align: center;">98.6</td> <td style="text-align: center;">77.6±1.0</td> </tr> </tbody> </table> </body> </html>

How to Use

vLLM (Recommended)

For high-performance inference and deployment, we recommend using vLLM. We also provide a standalone script for efficiently processing multi-page PDF documents. This script operates independently and does not require the official olmOCR toolkit, offering a lightweight and fast way to perform OCR on entire documents.

python DocLoom_test.py <pdf_file_path>

Note: We use olmOCR’s no_anchoring_v4 prompt. Please include the following instruction in the request.

Attached is one page of a document that you must process. Just return the plain text representation of this document as if you were reading it naturally. Convert equations to LateX and tables to HTML.\nIf there are any figures or charts, label them with the following markdown syntax ![Alt text describing the contents of the figure](page_startx_starty_width_height.png)\nReturn your output as markdown.

Acknowledgement

We express our gratitude to the teams that developed olmOCR and Qwen3-VL, which were instrumental in our research.