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

Video Question Answering research benchmarks – Page 17 · SOTA2 Research

Video Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

IntentQA (de-biased set)

video-grounded entailment tree reasoning

61Temporal Score

4

Feb 26, 2026

NExT-QA de-biased set

video-grounded entailment tree reasoning

60.8Temporal Reasoning Score

4

Feb 26, 2026

CineClipQA (test)

2.98Overall Score

4

Feb 27, 2026

1.17FTL (s)

4

Feb 26, 2026

71.3Accuracy

4

Feb 26, 2026

AGQA Balanced (more compositional steps) 2.0 (test)

48.09Binary Acc

4

Feb 26, 2026

AGQA Balanced indirect references 2.0 (test)

76.93Precision (Object-B)

4

Feb 26, 2026

AGQA Balanced novel compositions 2.0 (test)

50.88Sequencing (Binary) Acc

4

Feb 26, 2026

83.7MC Accuracy

4

Feb 26, 2026

MSVD Open Ended (OE)

48.9Accuracy

4

Feb 26, 2026

65.7Accuracy

4

Feb 26, 2026

EMCompress (Stage-1)

23Temporal Relational mIoU

3

Apr 28, 2026

79VQA Accuracy

3

Apr 23, 2026

Video-HOLMES stress (test)

32Average Score

3

Apr 23, 2026

41.25Accuracy

3

Feb 26, 2026

Video Understanding Task

1BLEU

3

Feb 26, 2026

60.36Accuracy

3

Feb 26, 2026

53.05MJ Score

3

Feb 26, 2026

39.85Acc

3

Feb 26, 2026

VideoMME original (test)

video-grounded entailment tree reasoning

55.9Temporal Score

3

Feb 26, 2026

TGIF-QA FrameQA (test)

51.4Accuracy

3

Feb 26, 2026

NExT-QA Hard Split - Causal

56.4Accuracy

3

Feb 26, 2026

NExT-QA Hard Split - Temporal

49.8Accuracy

3

Feb 26, 2026

RareAct V (test)

0.608Accuracy

3

Feb 26, 2026

ActivityNet-QA Y/N

79.9Accuracy

2

May 7, 2026

Page 17 of 18

Popular datasets

Video-MME VideoMME NExT-QA EgoSchema TGIF-QA

Follow for updates

Join SOTA2 Contact