Benchmark Almanac

MultipanelVQA

GPT-4o (snapshot unspecified) 76.8% tops its leaderboard Gemini 1.0 Pro Vision 72.3% leads the models we track
Not in model cards

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
In and out
Text, Images → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Vision
Last model added
January 2024
Scores refreshed
November 20th, 2026
8
Entries in its paper, 5 models we track

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:

  1. 1 GPT-4o (snapshot unspecified) 76.8%
  2. 2 Gemini 1.0 Pro Vision 72.3%
  3. 3 LLaVA-NeXT 69.9%
  4. 4 GPT-4V 64%
  5. 5 LLaVA-v1.5-13B 58.8%
  6. 6 MiniGPT-v2 48.7%
  7. 7 mPLUG-Owl2 45.4%
  8. 8 InstructBLIP FLAN-T5-XXL 45.4%

Source: The MultipanelVQA paper

#EntryScoreSettingDateSource
1 GPT-4o (snapshot unspecified) 76.8% Official leaderboard
2 Gemini 1.0 Pro Vision 72.3% Jan 2024 Official leaderboard
3 LLaVA-NeXT 69.9% Official leaderboard
4 GPT-4V 64% Nov 2023 Official leaderboard
5 LLaVA-v1.5-13B 58.8% Oct 2023 Official leaderboard
6 MiniGPT-v2 48.7% Official leaderboard
7 mPLUG-Owl2 45.4% Nov 2023 Official leaderboard
8 InstructBLIP FLAN-T5-XXL 45.4% Jun 2023 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 1.0 Pro Vision 72.3% Jan 2024 Official leaderboard
2 GPT-4V 64% Nov 2023 Official leaderboard
3 LLaVA-v1.5-13B 58.8% Oct 2023 Official leaderboard
4 mPLUG-Owl2 45.4% Nov 2023 Official leaderboard
5 InstructBLIP FLAN-T5-XXL 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. 1 GPT-4V ↑1 84.8%
  2. 2 Gemini 1.0 Pro Vision ↓1 81%
  3. 3 LLaVA-v1.5-13B 76.9%
  4. 4 mPLUG-Owl2 71.8%
  5. 5 InstructBLIP FLAN-T5-XXL 56.8%

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.

OpenAI Google DeepMind
Benchmark paper Not tested since Jan 2024

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.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2023 2024 Near the ceiling (85%) Gemini 1.0 Pro Vision GPT-4V LLaVA-v1.5-13B InstructBLIP FLAN-T5-XXL 0% 20% 40% 60% 80% 100% 2023 2024 Near the ceiling (85%) Gemini 1.0 Pro Vision GPT-4V

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

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

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.

How we check