MultipanelVQA
Models answer questions about images arranged into panels. The benchmark tests whether a model can locate the relevant panels and compare their contents.
- Made by
- Yue Fan and colleagues
- Released
- January 2024
- Kind
- General visual questions
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
- Last model added
- January 2024
- Scores refreshed
- November 20th, 2026
GPT-4o (snapshot unspecified) tops the leaderboard with 76.8% Gemini 1.0 Pro Vision leads with 72.3% among models released by January 2024
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports separate accuracies for synthetic and real-world data. The headline is their plain mean. 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. The best model we track is Gemini 1.0 Pro Vision, at 72.3%. This view shows only models we track, each at its best.
The newest model with a score here came out in January 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-4o (snapshot unspecified) 76.8%
- 2
Gemini 1.0 Pro Vision 72.3%
- 3 LLaVA-NeXT 69.9%
- 4 GPT-4V 64%
- 5
LLaVA-v1.5-13B 58.8%
- 6 MiniGPT-v2 48.7%
- 7
mPLUG-Owl2 45.4%
- 8
InstructBLIP FLAN-T5-XXL 45.4%
Source: The MultipanelVQA paper
- 1
Gemini 1.0 Pro Vision 72.3%
- 2 GPT-4V 64%
- 3
LLaVA-v1.5-13B 58.8%
- 4
mPLUG-Owl2 45.4%
- 5
InstructBLIP FLAN-T5-XXL 45.4%
Source: The MultipanelVQA paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o (snapshot unspecified) | 76.8% | Official leaderboard | ||
| 2 | | 72.3% | Jan 2024 | Official leaderboard | |
| 3 | LLaVA-NeXT | 69.9% | Official leaderboard | ||
| 4 | GPT-4V | 64% | Nov 2023 | Official leaderboard | |
| 5 | | 58.8% | Oct 2023 | Official leaderboard | |
| 6 | MiniGPT-v2 | 48.7% | Official leaderboard | ||
| 7 | | 45.4% | Nov 2023 | Official leaderboard | |
| 8 | | 45.4% | Jun 2023 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 72.3% | Jan 2024 | Official leaderboard | |
| 2 | GPT-4V | 64% | Nov 2023 | Official leaderboard | |
| 3 | | 58.8% | Oct 2023 | Official leaderboard | |
| 4 | | 45.4% | Nov 2023 | Official leaderboard | |
| 5 | | 45.4% | Jun 2023 | Official leaderboard |
Rankings by part
We read 8 parts from the benchmark’s paper in 3 groups: synthetic data, subset and real-world data. Each ranks models on one part of the test. Gemini 1.0 Pro Vision leads 7 of them, and GPT-4V leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Q1
5 models we track have a score here.
- 1 GPT-4V ↑1 84.8%
- 2
Gemini 1.0 Pro Vision ↓1 81%
- 3
LLaVA-v1.5-13B 76.9%
- 4
mPLUG-Owl2 71.8%
- 5
InstructBLIP FLAN-T5-XXL 56.8%
Q2
5 models we track have a score here.
- 1
Gemini 1.0 Pro Vision 72.5%
- 2 GPT-4V 62.5%
- 3
LLaVA-v1.5-13B 58.7%
- 4
mPLUG-Owl2 47.9%
- 5
InstructBLIP FLAN-T5-XXL 46.3%
Q3
5 models we track have a score here.
- 1
Gemini 1.0 Pro Vision 63.2%
- 2
InstructBLIP FLAN-T5-XXL ↑3 50.3%
- 3 GPT-4V ↓1 38.4%
- 4
LLaVA-v1.5-13B ↓1 36.6%
- 5
mPLUG-Owl2 ↓1 20.9%
Synthetic data
5 models we track have a score here.
- 1
Gemini 1.0 Pro Vision 72.2%
- 2 GPT-4V 61.9%
- 3
LLaVA-v1.5-13B 57.4%
- 4
InstructBLIP FLAN-T5-XXL ↑1 51.1%
- 5
mPLUG-Owl2 ↓1 46.9%
Real-world data
5 models we track have a score here.
- 1
Gemini 1.0 Pro Vision 72.4%
- 2 GPT-4V 66%
- 3
LLaVA-v1.5-13B 60.1%
- 4
mPLUG-Owl2 43.9%
- 5
InstructBLIP FLAN-T5-XXL 39.6%
Q1
5 models we track have a score here.
- 1
Gemini 1.0 Pro Vision 81.1%
- 2 GPT-4V 78.1%
- 3
LLaVA-v1.5-13B 69.7%
- 4
mPLUG-Owl2 53.9%
- 5
InstructBLIP FLAN-T5-XXL 44.4%
Q2
5 models we track have a score here.
- 1
Gemini 1.0 Pro Vision 72.3%
- 2 GPT-4V 68.3%
- 3
LLaVA-v1.5-13B 57.8%
- 4
InstructBLIP FLAN-T5-XXL ↑1 50.4%
- 5
mPLUG-Owl2 ↓1 44.6%
Q3
5 models we track have a score here.
- 1
Gemini 1.0 Pro Vision 64%
- 2
LLaVA-v1.5-13B ↑1 52.8%
- 3 GPT-4V ↓1 51.6%
- 4
mPLUG-Owl2 33.1%
- 5
InstructBLIP FLAN-T5-XXL 24%
2 models have held number one in the benchmark’s paper since its release in January 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The MultipanelVQA paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official MultipanelVQA 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in January 2024, for Gemini 1.0 Pro Vision. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (8 entries).
- Pass Models scored 5 models we track, plus 3 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in January 2024, for Gemini 1.0 Pro Vision.
- Note Frontier models None of its models are on the capabilities index.
- Pass Headroom The best is 72.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 5 rows for models we track and 3 other entries at the last read.
- 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.