MP-DocVQA
Models answer questions about scanned documents of up to 20 pages, where the answer sits on one page. Scored by ANLS against the reference answer.
It extends the single-page DocVQA questions to multi-page documents. Microsoft's Mage-VL card reports it as MultiDocVQA-val.
- Released
- December 2022
- Kind
- Documents, charts and text in images
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
In the authors’ words
Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple pages that should be processed altogether. In this work we extend DocVQA to the multi-page scenario. For that, we first create a new dataset, MP-DocVQA, where questions are posed over multi-page documents instead of single pages. Second, we propose a new hierarchical method, Hi-VT5, based on the T5 architecture, that overcomes the limitations of current methods to process long multi-page documents. The proposed method is based on a hierarchical transformer architecture where the encoder summarizes the most relevant information of every page and then, the decoder takes this summarized information to generate the final answer. Through extensive experimentation, we demonstrate that our method is able, in a single stage, to answer the questions and provide the page that contains the relevant information to find the answer, which can be used as a kind of explainability measure.
rubentito/hivt5-base-mpdocvqa tops the leaderboard with 62%
Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1 rubentito/hivt5-base-mpdocvqa MP-DocVQA fine-tuned 62%
- 2 rubentito/longformer-base-mpdocvqa MP-DocVQA fine-tuned 52.9%
- 3 rubentito/t5-base-mpdocvqa MP-DocVQA fine-tuned 50.5%
- 4 rubentito/bigbird-base-itc-mpdocvqa MP-DocVQA fine-tuned 49.3%
- 5 rubentito/layoutlmv3-base-mpdocvqa MP-DocVQA fine-tuned 45.4%
- 6 rubentito/bert-large-mpdocvqa MP-DocVQA fine-tuned 41.8%
Source: Official MP-DocVQA leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | rubentito/hivt5-base-mpdocvqa | 62% | MP-DocVQA fine-tuned | Official leaderboard | |
| 2 | rubentito/longformer-base-mpdocvqa | 52.9% | MP-DocVQA fine-tuned | Official leaderboard | |
| 3 | rubentito/t5-base-mpdocvqa | 50.5% | MP-DocVQA fine-tuned | Official leaderboard | |
| 4 | rubentito/bigbird-base-itc-mpdocvqa | 49.3% | MP-DocVQA fine-tuned | Official leaderboard | |
| 5 | rubentito/layoutlmv3-base-mpdocvqa | 45.4% | MP-DocVQA fine-tuned | Official leaderboard | |
| 6 | rubentito/bert-large-mpdocvqa | 41.8% | MP-DocVQA fine-tuned | Official leaderboard |
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
- 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%
- 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%
- ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9%