Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-20

Visual Question Answering

3260 papers • 126 benchmarks • 313 datasets

MLLM Leaderboard

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in visual-question-answering-20

Trend

Dataset

Best Model

Actions

MM-Vet

MM-Vet

MM-Vet v2

MM-Vet v2

ViP-Bench

ViP-Bench

Libraries

i

Use these libraries to find visual-question-answering-20 models and implementations

huggingface/transformers

8 papers 146,985

Datasets

No datasets available.

Subtasks

Spatial Reasoning Object Hallucination Explanatory Visual Question Answering Vietnamese Visual Question Answering Vietnamese Visual Question Answering

Most implemented papers

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

VQA v2 test-dev

VQA v2 test-dev

BenchLMM

BenchLMM

MMBench

MMBench

V*bench

V*bench

VQA v2 val

VQA v2 val

MSRVTT-QA

MSRVTT-QA

VQA v2 test-std

VQA v2 test-std

MSVD-QA

MSVD-QA

VQA v2

VQA v2

PlotQA-D1

PlotQA-D1

PlotQA-D2

PlotQA-D2

MMHal-Bench

MMHal-Bench

TextVQA test-standard

TextVQA test-standard

COCO Visual Question Answering (VQA) real images 2.0 open ended

COCO Visual Question Answering (VQA) real images 2.0 open ended

GRIT

GRIT

VizWiz

VizWiz

MM-Vet (w/o External Tools)

MM-Vet (w/o External Tools)

COCO (Common Objects in Context)

COCO (Common Objects in Context)

EarthVQA

EarthVQA

VisualMRC

VisualMRC

AMBER

AMBER

GQA

GQA

CLEVR

CLEVR

MapEval-Visual

MapEval-Visual

SIRI-WHU

SIRI-WHU

AID-VQA

AID-VQA

RSVQA-HR

RSVQA-HR

salesforce/lavis

5 papers 10,743

gabegrand/adversarial-vqa

4 papers 12

Adding a benchmark result helps the community track progress.

Visual Question Answering | State-of-the-Art