oneshotlm
Compare all models on this prompt →

Reaction-diffusion · grok-4.6

Run a Gray-Scott reaction-diffusion simulation on a canvas that grows organic Turing patterns in real time, with the mouse seeding new growth.

⛨ sandboxed Open in new tab ↗
transcript · 4 messages
user

Run a Gray-Scott reaction-diffusion simulation on a canvas that grows organic Turing patterns in real time, with the mouse seeding new growth.

assistant
thinking
The user wants me to build a single-page web app - a Gray-Scott reaction-diffusion simulation on a canvas that grows organic Turing patterns in real time, with mouse seeding new growth. Everything in ...

I'll build a self-contained Gray-Scott canvas sim with live Turing patterns and mouse seeding, all in one `index.html`.

write /tmp/ws/index.html (14671 bytes)
toolResult

Successfully wrote 14671 bytes to /tmp/ws/index.html

assistant
thinking
The user asked me to build a Gray-Scott reaction-diffusion simulation. I've written a complete self-contained index.html. Let me verify the file exists.

`index.html` is in the working directory — a self-contained Gray–Scott sim. - **Live RD**: U/V on a toroidal grid, 9-point Laplacian, feed/kill (`F`, `k`) plus `Du`/`Dv`/`dt` - **Mouse**: click/drag inoculates V so new growth nucleates under the brush - **Presets**: coral, mitosis, spots, worms, maze, waves - **Controls**: sliders, random seed, clear, pause - **No network**: all CSS/JS inline, no CDNs Open `index.html` in a browser; patterns organize over a few seconds.

TAKE IT TO CODE

A single self-contained HTML file — copy it and open in any browser, or reuse the prompt with your own pi-agent run.

RUN

modelgrok-4.6
vendorxAI · Grok
harnesspi-agent
generated2026-08-13

EVALUATION

4/5 working

Gray-Scott reaction-diffusion animates continuously and evolves into organic Turing patterns; mouse click/drag/wheel show subtle changes.

Vision grade · anthropic/claude-sonnet-5

MEASUREMENTS

Raw readings from the capture, not a verdict — the grade above is the only judgement. Percentages are how much of the screen changed; the measure under-reports sparse motion on a dark background.

idle motion23.8%
on click3.6%
on drag1.2%
on wheel0.0%
on enter + space0.0%
on arrow keys0.0%
on w/a/s/d0.0%
frame spread9.7 / 255
console errors0
js errors none

METRICS

runtime61.6s
tokens in8.3k
tokens out5.4k
cached3.1k
cost / run$0.0441