oneshotlm
Compare all models on this prompt →

Double pendulum · qwen3-vl-30b-a3b-instruct

Simulate a chaotic double pendulum on a canvas using the correct equations of motion, drawing the arms and a colorful fading trail of the tip.

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

Simulate a chaotic double pendulum on a canvas using the correct equations of motion, drawing the arms and a colorful fading trail of the tip.

assistant

I'll create a single-page web app that simulates a chaotic double pendulum with a colorful fading trail. The simulation will use the correct equations of motion for a double pendulum.

write index.html (7680 bytes)
toolResult

Successfully wrote 7680 bytes to index.html

assistant

I've created a single-page web app that simulates a chaotic double pendulum with the correct equations of motion. The simulation uses the Runge-Kutta 4th order method for numerical integration to accurately model the pendulum's behavior. The app features: - A colorful fading trail of the tip of the second arm - Realistic physics based on the double pendulum equations of motion - Smooth animation using requestAnimationFrame - Proper rendering of both arms and bobs The simulation runs in a full-screen canvas, with the pendulum starting from an initial position where both arms are at 90 degrees (vertical) with small initial velocities to create chaotic behavior. To use this app, simply open the index.html file in any modern browser. The pendulum will immediately start animating, showing the characteristic chaotic motion of a double pendulum system.

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

modelqwen3-vl-30b-a3b-instruct
vendorQwen
harnesspi-agent
generated2026-08-01

EVALUATION

3/5 working

Double pendulum swings continuously with a colorful fading trail, but pendulum stays small in a corner and inputs cause no distinct change.

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 motion0.9%
on click1.1%
on drag1.1%
on wheel1.2%
on enter + space1.2%
on arrow keys1.1%
on w/a/s/d1.0%
frame spread6.9 / 255
console errors0
js errors none

METRICS

runtime22.5s
tokens in5.4k
tokens out2.6k
cached0
cost / run$0.0021