Benchmark Almanac

MPDocBench-Parse

In use

Models parse complete multipage documents while preserving content and cross-page structure. Evaluation scores text, formulas, tables, figure extraction, reading order, and heading hierarchy.

The benchmark contains 433 documents and 3,246 pages in English and Chinese. Cross-page text and table merging contribute to the document-level evaluation.

Released
May 2026
Kind
Documents, charts and text in images
Level
Expert
Scored
Checked automatically
Answers
Short answer
Measures
Capability
Language
English, Chinese
In and out
Documents → Text, Tables, Images
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Last in a launch post
October 2026
Last model added
October 2026

In the authors’ words

Document parsing converts visually rich documents into machine-readable structured representations, forming a crucial foundation for information systems. Although many benchmarks have been proposed for document parsing, they remain inadequate for realistic scenarios. Existing benchmarks either focus on specific tasks or assess only single-page, text-centric settings, making them insufficient for practical multi-page parsing. Moreover, they lack fine-grained evaluation of semantic continuity, hierarchical structure recovery, and visual content preservation. To address these gaps, we propose MPDocBench-Parse, a benchmark for multi-page document parsing in real-world applications. It contains 433 manually annotated documents with 3,246 pages, covering 15 document types in English and Chinese, with diverse layout styles, and supports document-level end-to-end evaluation. We further design a comprehensive protocol for content fidelity and logical structure, covering text, table, and formula recognition, truncated text and table merging, figure extraction, reading order, and heading hierarchy recovery. Experiments show that, while existing models perform well on basic text extraction, they still suffer clear limitations in semantic continuity integration, visual content parsing, and hierarchical structure recovery. MPDocBench-Parse provides a unified foundation for advancing document parsing toward more realistic scenarios.

Abstract of MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing (arXiv:2605.22100, CC0)
1
Model scored in lab cards
1
Launch post lists it, from 1 lab

Unlimited OCR 2 leads with 84.6%

Best score per model as labs report them in their own cards, drawn striped. Labs pick their own settings, so these compare less cleanly than independent runs.

  1. 1 Unlimited OCR 2 84.6%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Unlimited OCR 2 84.6% Oct 2026 Lab model card

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card
0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Unlimited OCR 2 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Unlimited OCR 2

Source: Labs’ model cards

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Baidu
DateLaunch postScoreAs the post writes it
Oct 27, 2026 Unlimited OCR 2 84.6 MPDocBench Overall

More in Vision

All 636 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. Qwen 3.6 Plus 86%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy. Seed2.1 Pro 90.7%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%

Data audit

4 of 5 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Note Independent runs Only labs’ own numbers, so no one else has checked them. Scores from launch posts (1 score).
  • Note Models scored Only 1 model we track.
  • Pass Newest score The newest is from October 2026, for Unlimited OCR 2.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 84.6%, under 85%, so it still separates models.
Leaderboard import 1 note
  • Note Importer No public leaderboard to read.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check