HyperAI

Explanation Generation On Whoops

Metrics

Human (%)

Results

Performance results of various models on this benchmark

Comparison Table
Model NameHuman (%)
breaking-common-sense-whoops-a-vision-and33
vlis-unimodal-language-models-guide-
breaking-common-sense-whoops-a-vision-and15
breaking-common-sense-whoops-a-vision-and27
vlis-unimodal-language-models-guide-
breaking-common-sense-whoops-a-vision-and68
breaking-common-sense-whoops-a-vision-and0