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 24 · SOTA2 Research

Visual Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

VQAv2 3K curated MS COCO (test)

7.4Relative Performance Drop (%)

10

Apr 21, 2026

HGI SemiosisArt

93.2Accuracy

10

Apr 13, 2026

54.9Accuracy

10

Apr 7, 2026

VQA Adversarial, epsilon_a = 4/255 v2

42.6VQA Accuracy

10

Mar 31, 2026

VQA Clean v2 (test)

74.5Accuracy (VQA)

10

Mar 31, 2026

TextVQA Adversarial, epsilon_a = 4/255

17.2VQA Accuracy

10

Mar 31, 2026

TextVQA Clean (test)

37.1VQA Accuracy

10

Mar 31, 2026

88.9Accuracy

10

Jun 17, 2026

MSVQA Indoor T=5 (test)

87.2Last Performance (At)

10

Mar 16, 2026

MSVQA Low altitude T=5 (test)

59.8Last Performance (At)

10

Mar 16, 2026

MSVQA Underwater T=5 (test)

84.27Last Performance (At)

10

Mar 16, 2026

MSVQA High altitude T=5 (test)

64.97Last Performance (At)

10

Mar 16, 2026

21.6F1 Score

10

Mar 13, 2026

74.4F1 Score

10

Mar 13, 2026

3DRad 1.0 (test)

79.28Accuracy

10

Mar 13, 2026

77.79Accuracy

10

Mar 13, 2026

ScienceQA (val)

82.9Accuracy

10

May 26, 2026

SpaceQwen2.5-VL-3B-Instruct

96.9Accuracy

10

Mar 10, 2026

78.94Presence Accuracy

10

Mar 4, 2026

92.68Presence

10

Mar 4, 2026

64.2Accuracy

10

Feb 27, 2026

IRIS 1.0 (ambiguous trials)

59.3Accuracy (Image Only)

10

Feb 26, 2026

ViTextVQA (test)

53.95F1 Score

10

Feb 26, 2026

61.9BD Metric

10

Mar 4, 2026

VQA Benchmarks GQA, MMB, MME, POPE, SQA, TextVQA

64.2GQA Score

10

Feb 26, 2026

Page 24 of 46

Popular datasets

VQA GQA TextVQA Clevr Vizwiz

Follow for updates

Join SOTA2 Contact