The benchmarks section lists all benchmarks using a given dataset or any of
its variants. We use variants to distinguish between results evaluated on
slightly different versions of the same dataset. For example, ImageNet 32⨉32
and ImageNet 64⨉64 are variants of the ImageNet dataset.
The data consists of a set of 3 task types and 4 question types, creating 12 total scenarios. The tasks are grouped into stories, which are denoted by the numbering at the start of each line.