Verified65% confidenceFactExact time
Simon Willison uses SVG generation of "a pelican riding a bicycle" as an informal benchmark test of model capabilities.
3
Sources
65%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
Related Claims
UnverifiedSimon Willison has long used 'a pelican riding a bicycle' as a fixed test case to comparatively evaluate different AI models across different time periods.73% similarUnverifiedThe "draw a pelican riding a bicycle" test was originally proposed by developer Simon Willison to evaluate the capability boundaries of large language models and image generation models.71% similarUnverifiedBenchmark test sets specifically targeting physical plausibility have emerged, such as EvalCrafter and PhyGenBench.59% similarUnverifiedA benchmark called JevBench has emerged, specifically designed to compare Jev-class decision models.57% similarUnverifiedThe pelican test is a composite evaluation combining code generation and visual reasoning, typically using Python with drawing libraries such as matplotlib, turtle, or SVG.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/500649API
curl https://kongchang.com/api/v1/knowledge/claims/500649MCP
get_claim(id=500649)