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 33 · SOTA2 Research

Visual Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

TableVQA-Bench v1 (test)

Qwen2.5-VL-7B-Instruct

82VTabFact

6

Apr 23, 2026

BridgeVQA (test)

DR-MMSearchAgent

44.6Accuracy

6

Apr 23, 2026

OmniDrive (test)

CogDriver-Agent

86.67CI-r

6

Apr 21, 2026

58.3Accuracy

6

Apr 16, 2026

72.3Tokenized F1

6

Apr 8, 2026

92.2Modality Accuracy

6

Apr 6, 2026

97.7Modality Accuracy

6

Apr 6, 2026

94.5Modality Accuracy

6

Apr 6, 2026

94.5Modality Accuracy

6

Apr 6, 2026

85.6Normalized Accuracy

6

Mar 30, 2026

60.5Normalized Accuracy

6

Mar 30, 2026

81.2VQA Score

6

Mar 24, 2026

InstaOrder Occ. (val)

Qwen3-VL-4b-Instruct

85.2Accuracy

6

Mar 12, 2026

InstaOrder Depth (val)

66.1Accuracy

6

Mar 12, 2026

SNs (maj. voting)

93.7Accuracy

6

Mar 12, 2026

MathVision mini

22.7Accuracy

6

Mar 12, 2026

MMBench CN V1.1 (dev)

56.66Accuracy

6

Mar 12, 2026

MMBench EN V1.1 (dev)

58.75Accuracy

6

Mar 12, 2026

COCO FuzzingRL probes (held-out)

100Accuracy

6

Mar 10, 2026

71.384Precision

6

Mar 4, 2026

RSVQA-HRBEN (test)

67.35Presence Accuracy

6

Feb 27, 2026

RSVQA-LRBEN (test)

92.58Presence Accuracy

6

Feb 27, 2026

73.5F1 (Q1)

6

Feb 26, 2026

VQA AttackVLM (test)

87.9FCS

6

Feb 27, 2026

0.88FCS Score

6

Feb 27, 2026

Page 33 of 46

Popular datasets

VQA GQA TextVQA Clevr Vizwiz

Follow for updates

Join SOTA2 Contact