Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Visual Question Answering research benchmarks – Page 16 · SOTA2 Research

Visual Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

A-OKVQA POPE Evaluation (Adversarial)

82Accuracy

16

Apr 10, 2026

A-OKVQA POPE (Popular)

89.77Accuracy

16

Apr 10, 2026

A-OKVQA POPE Evaluation (Random)

90.03Accuracy

16

Apr 10, 2026

88.77CIDEr

16

Apr 6, 2026

77.23Overall Accuracy

16

Mar 24, 2026

Path-VQA (test)

Llama-3.2-11B-Vision-Instruct

2.69Commonsense Score

16

Mar 23, 2026

67.1Score

16

Mar 10, 2026

MiMo-Embodied-7B

69.9Accuracy

16

Mar 4, 2026

LLaVA-NeXT Vanilla 7B

64.2Accuracy

16

Mar 4, 2026

LLaVA-NeXT-7B (Upper Bound)

62.9Accuracy

16

Feb 27, 2026

LLaVA-NeXT-7B (Upper Bound)

81.2Accuracy

16

Feb 27, 2026

CLEAR Forget 1.0

Visual Knowledge Distillation

34.2Accuracy

16

Feb 26, 2026

MLLMU-Bench Real-world 1.0

77.3Accuracy

16

Feb 26, 2026

MLLMU-Bench Retain 1.0

56Accuracy

16

Feb 26, 2026

MLLMU-Bench Forget 1.0

Visual Knowledge Distillation

29.8Accuracy

16

Feb 26, 2026

86.21Overall Accuracy

16

Feb 26, 2026

FloodNet (test)

83.84OA

16

Feb 26, 2026

GoG-3-8B-Think-RL

48.02Accuracy

16

Feb 26, 2026

MMBench Chinese V1.1

83Accuracy

16

Feb 26, 2026

MUSIC-AVQA v1.0 (test)

0.84Accuracy (Count)

16

Feb 26, 2026

63.17F1 Score

16

Mar 6, 2026

INST-IT Bench Image

84.8MC Accuracy

16

Feb 26, 2026

VizWiz-QA (val)

88.7AUC

16

Feb 26, 2026

63.8Accuracy

16

Mar 12, 2026

LLaVA-RLHF_13B×336

60.1Overall Score

16

May 26, 2026

Page 16 of 46

Popular datasets

VQA GQA TextVQA Clevr Vizwiz

Follow for updates

Join SOTA2 Contact