Explanation Generation On Whoops
Metrics
Human (%)
Results
Performance results of various models on this benchmark
Comparison Table
Model Name | Human (%) |
---|---|
breaking-common-sense-whoops-a-vision-and | 33 |
vlis-unimodal-language-models-guide | - |
breaking-common-sense-whoops-a-vision-and | 15 |
breaking-common-sense-whoops-a-vision-and | 27 |
vlis-unimodal-language-models-guide | - |
breaking-common-sense-whoops-a-vision-and | 68 |
breaking-common-sense-whoops-a-vision-and | 0 |