← All benchmarks
Bizarre Plush Toy Web Catalog
Three AI models interpret an intentionally open-ended brief: a website catalog full of bizarre, unique plush toys. Stress-tests creative range under loose constraints, multi-subject density in one frame, and website-UI rendering (thumbnails, titles, prices, filters).
7 models compared · same input · same prompt
Run it on your idea
Run your own prompt across all 7 models
Don’t just compare ours — get every model’s take on your idea, side by side. Full-res, one click. No juggling 7 accounts.
Input & prompt
Prompt template
Can you generate an image of a screenshot of a website catalog displaying dozens of very interesting, unique plush toys. Like alien plushes for example. Something very bizarre, be creative with it.
ChatGPT (GPT Image 2)
Try this →88.4sopenai/gpt-image-2
Nano Banana 2 (Gemini)
Try this →14.1sgoogle/nano-banana-2
Grok Imagine Pro
Try this →19.8sx-ai/grok-imagine-image-pro
Qwen Image 2.0 Pro
Try this →Seedream 5 Lite
Try this →Flux Kontext Pro
Try this →Nano Banana 2 Lite
Try this →Want to try this with your own twist?
Run the same prompt with your own variables — it's free.
Try the prompt →New benchmark every week
We put the latest models head to head on the same brief — no labels, you judge. Get each new benchmark in your inbox the morning it drops.