oneshotlm
Compare all models on this prompt →

Boids flocking · glm-5.3

Create a full-screen flocking simulation of boids using separation, alignment, and cohesion, drawn as oriented triangles that steer smoothly and flee from the mouse cursor.

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

Create a full-screen flocking simulation of boids using separation, alignment, and cohesion, drawn as oriented triangles that steer smoothly and flee from the mouse cursor.

assistant
write index.html (5886 bytes)
toolResult

Successfully wrote 5886 bytes to index.html

assistant

Done — `index.html` in the current directory contains the full simulation: - **220 boids** drawn as oriented triangles (nose pointing along velocity), colored by hue and speed - **Classic Reynolds rules**: separation (inverse-distance weighted), alignment, and cohesion, each applied through smooth limited steering forces - **Mouse flee**: boids panic within a 130px radius, with a force ramping up as you get closer (fear radius drawn as a faint circle) - **Soft edge containment** so flocks turn back from screen edges instead of clipping - Speed clamping (min/max) plus subtle motion trails via semi-transparent frame redraws Open it in any browser — everything is self-contained with no external resources.

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

modelglm-5.3
vendorZ.ai · GLM
harnesspi-agent
generated2026-08-27

EVALUATION

4/5 working

Boids flock in colorful triangle groups continuously animating, with a visible cursor-avoidance circle affecting flocks near it.

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 motion9.1%
on click12.8%
on drag12.8%
on wheel12.0%
on enter + space12.1%
on arrow keys9.1%
on w/a/s/d10.8%
frame spread14.3 / 255
console errors0
js errors none

METRICS

runtime24.8s
tokens in4.9k
tokens out2.1k
cached2.8k
cost / run$0.0129