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

Vision-Language Reasoning research benchmarks – Page 2 · SOTA2 Research

Vision-Language Reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

CLEVR CoGenT (Split B)

78.8Accuracy

3

Feb 26, 2026

CLEVR-CoGenT (Split A)

99.7Accuracy

3

Feb 26, 2026

CLEVR-SYN hard (val)

73.4Accuracy

2

Feb 26, 2026

CLEVR-SYN medium (val)

81.2Accuracy

2

Feb 26, 2026

CLEVR-SYN easy (val)

92.1Accuracy

2

Feb 26, 2026

SelfEval Benchmark (test)

55.4Attribute Binding

2

Feb 26, 2026

Page 2 of 2

Popular datasets

MMStar Clevr Winoground CLEVR-SYN VL Reasoning Benchmarks

Follow for updates

Join SOTA2 Contact