List your company

ResearchFormerly WizWand

Vision-Language Reasoning

Benchmarks

DatasetSOTA 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