DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to compare your OCR pipeline on the MarathonDocBench ultra-long benchmark with Unlimited OCR

Use Baidu's new MarathonDocBench dataset to test how your current OCR handles very long documents.

Short answer: Get MarathonDocBench from Hugging Face (baidu/MarathonDocBench); then run your current OCR on a sample of its documents; run Unlimited OCR 2 with infer_multi on the same documents. All steps.

Who it is forA team choosing an OCR model for long reports, contracts or books.

The problemMost OCR benchmarks use single pages, so they hide how models fail on long documents.

The outcomeA side by side comparison of your current OCR and Unlimited OCR 2 on long documents.

What you need first

  • An NVIDIA GPU (tested on an A800 80GB) with CUDA
  • Python 3.10 with torch 2.13.0 and transformers 4.52.1, or uv for the SGLang setup
  • PyMuPDF to convert PDFs to page images

Steps

  1. Get MarathonDocBench from Hugging Face (baidu/MarathonDocBench)
  2. Run your current OCR on a sample of its documents
  3. Run Unlimited OCR 2 with infer_multi on the same documents
  4. Compare outputs, and try the Hugging Face Spaces demo for quick checks

Prompt for your agent

Download baidu/MarathonDocBench, pick 5 long documents, run both <my OCR tool> and baidu/Unlimited-OCR-2 (infer_multi) on them, and write a comparison of where each fails.

Caveat.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for baidu/Unlimited-OCR and "Compare your OCR pipeline on the MarathonDocBench ultra-long benchmark"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer