MMDocIR
Models find relevant pages or layout elements inside long documents that contain both text and visual material.
The benchmark evaluates page retrieval and layout retrieval separately.
- Made by
- Kuicai Dong and colleagues
- Released
- January 2025
- Kind
- Documents, charts and text in images
- Level
- University
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
Col-Phi3 tops the leaderboard with 44%
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. This is the plain mean of macro Recall@1 on page retrieval and layout retrieval. 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 Col-Phi3 44%
- 2 ColPali 42.9%
- 3 DPR-Phi3 41.8%
- 4 DSEdocmatix 39%
- 5 ColBERT 38.5%
- 6 DSEwiki−ss 38.1%
- 7 Contriever 34.6%
- 8 BGE 34.5%
- 9 E5 33.8%
- 10 GTE 32.5%
- 11 DPR 23.3%
Source: The MMDocIR paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Col-Phi3 | 44% | Official leaderboard | ||
| 2 | ColPali | 42.9% | Official leaderboard | ||
| 3 | DPR-Phi3 | 41.8% | Official leaderboard | ||
| 4 | DSEdocmatix | 39% | Official leaderboard | ||
| 5 | ColBERT | 38.5% | Official leaderboard | ||
| 6 | DSEwiki−ss | 38.1% | Official leaderboard | ||
| 7 | Contriever | 34.6% | Official leaderboard | ||
| 8 | BGE | 34.5% | Official leaderboard | ||
| 9 | E5 | 33.8% | Official leaderboard | ||
| 10 | GTE | 32.5% | Official leaderboard | ||
| 11 | DPR | 23.3% | Official leaderboard |
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 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.
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
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (11 entries).
- Pass Models scored 11 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 11 entries at the last read, none a model we track.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
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.