Why we chose this prompt: Simon Willison's informal benchmarkOpens in new tab for text models, run verbatim since late 2024. Text models cannot draw, but they can write code and SVG is code. The task is hard on purpose. Bicycle frames are difficult to remember, pelicans are difficult to draw, and pelicans cannot ride bicycles. Each model gets the prompt with no examples or style guidance, so the picture reflects its own judgment.
Generate an SVG of a pelican riding a bicycle
Generate an SVG of a pelican riding a bicycle