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 12 · SOTA2 Research

Video Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Ego-in-Exo Perception (Ego-Exo4D)

81.8Action Understanding Accuracy

8

Jul 9, 2026

LongVideoBench (LVB)

Qwen2-VL + ReQuest

66.3Accuracy

8

Jul 3, 2026

WalkieKnowledge (original)

66.28Answer Accuracy

8

Jun 17, 2026

45.4Accuracy

8

Jun 1, 2026

55,136.3Average Context Length (tokens)

8

May 27, 2026

EventBench 60-1800s (test)

InternVL3.5-8B + EC-RAG

62.28Contextual Accuracy

8

May 8, 2026

NExT-QA 5-180s (test)

InternVL3.5-8B + EC-RAG

80.54Accuracy

8

May 8, 2026

HourVideo v1.0 (test)

33.4Overall Accuracy

8

Mar 5, 2026

Active Memory Benchmark

VideoMindPalace

44.7Q1

8

Mar 5, 2026

VideoMME Overall 1.0 (test)

68.3Accuracy

8

Feb 26, 2026

VideoMME Medium 1.0 (test)

66.6Accuracy

8

Feb 26, 2026

Movie-Chat Global Mode

88.72Accuracy

8

Feb 26, 2026

MVBench 2024 (test)

64.6Accuracy

8

Feb 26, 2026

LVBench 2024 (test)

66.7Accuracy

8

Feb 26, 2026

60.8Ling-Judge

8

Feb 26, 2026

VideoMME w/o sub. 1.0 (test)

MiMo-VL-7B + TCS

65Overall Acc

8

Feb 26, 2026

45.4Accuracy

8

Feb 26, 2026

TVQA zero-shot (test)

TOPA-Llama2-13B

50.2Accuracy

8

Feb 26, 2026

71Total Accuracy

8

Feb 26, 2026

53.44Accuracy (V+S)

8

Feb 26, 2026

44.05Attribute Accuracy

8

Feb 26, 2026

LSMDC Multiple Choice

84.4Accuracy

8

Feb 26, 2026

OL-VideoQA (test)

46.98BLEU-1

8

Feb 26, 2026

MovieQA v1 (test)

36.25Accuracy

8

Feb 26, 2026

MovieQA v1 (val)

38.67Accuracy

8

Feb 26, 2026

Page 12 of 18

Popular datasets

Video-MME VideoMME NExT-QA EgoSchema TGIF-QA

Follow for updates

Join SOTA2 Contact