HyperAI

Visual Reasoning On Winogavil

Metrics

Jaccard Index

Results

Performance results of various models on this benchmark

Comparison Table
Model NameJaccard Index
winogavil-gamified-association-benchmark-to15
winogavil-gamified-association-benchmark-to38
winogavil-gamified-association-benchmark-to40
winogavil-gamified-association-benchmark-to41
winogavil-gamified-association-benchmark-to90
winogavil-gamified-association-benchmark-to52
winogavil-gamified-association-benchmark-to46
winogavil-gamified-association-benchmark-to35