Knowledge
Visual Riddles
Visual Riddles: a commonsense and world-knowledge challenge for large vision and language models. Each item is an AI-generated image with an open-ended question requiring visual reasoning plus world knowledge. Per-(model, item) responses are human-rated correct/incorrect on the open-ended task.
793items
8subjects
Apache-2.0 declared; see upstream card for commercial-training restriction and retained image rightslicense
reasoningdomain
knowledgedomain
imagemodality
textmodality
item-level responses released
Saturation status: No
Response matrix
Loading response matrix…
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect