Thirty Replacement Prompts for the Pelican-on-a-Bicycle Test, Generated Because the Original Is Contaminated
Tom Gally / Hacker News (122pts, 44 comments)·low signal
Tom Gally funded a September 14 page of thirty SVG drawing prompts built in the style of Simon Willison's pelican benchmark, on the premise that the original prompt is now too well known to measure anything. Substitutes include an octopus operating a pipe organ, a giraffe assembling a grandfather clock and a penguin juggling chainsaws, run against GPT-6 Astra, Claude Fable 5.1, Gemini 3.8 Flash, DeepSeek V4 Pro, Qwen3.8 Max and Fugu Ultra v2, with generation time and cost shown per model and images displayed exactly as returned. The site itself says it was built by Claude Fable 5.1.