LLM Test Prompts

All prompts › Simulations & physics

Autonomous aquarium with wandering fish

Simulations & physicseasybuild testPrompt in EnglishHTMLcanvassmall models

What it tests: Object-oriented animation basics: 10–15 fish with wandering behaviour, smooth turning at the tank edges, facing the direction of travel, and delta-time updates. It separates very small models from usable ones.

Prompt length: 5,253 characters, roughly 1,310 tokens (estimate). · Side-by-side outputs of local models (results pages linked in the repo README) ↗

Autonomous Aquarium Simulation **Goal:** Create a visually appealing simulation of fish swimming in an aquarium environment using HTML, JS, and CSS. Demonstrate javascript best practices for object-oriented design, …

The source has no licence that allows copying, so only a short excerpt is shown here. The full prompt is one click away at the source.

How to grade it

Fish move continuously, change direction gradually, stay inside the canvas and turn smoothly near the edges, face their direction of travel, and move at the same speed regardless of frame rate. Note: the prompt's boilerplate looks up 'gameCanvas' while the canvas id is 'simulationCanvas', and it has two <body> blocks. Strong models notice and fix this; weak ones copy it and render nothing.

Scorecard tick what the model got right: 0/4

Runs in your browser; nothing is saved or sent.

0/4

Where models usually fail

A blank page because the canvas id mismatch was copied; fish flipping direction instantly at walls; movement tied to the frame rate.

Running it

Made for local models via llama.cpp or KoboldCpp; the repo has a runner and side-by-side result pages.

Source

Author
David Harris (GitHub @electricazimuth)
From
LocalLLM_VisualCodeTest
Exact file or post
https://github.com/electricazimuth/LocalLLM_VisualCodeTest/blob/7e7004885221fafb8b1de360cacc2b8281cf934a/code_prompts/aquarium.md
Licence
No license file (all rights reserved)
How we use it
Excerpt only: open the full prompt at the source

Testing a local model? Check first whether it fits your hardware with Can I run this LLM?

More in Simulations & physics