oneshotlm
Compare all models on this prompt →

Boids flocking · kat-coder-air-v2.5

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 /tmp/ws/index.html (8032 bytes)
toolResult

Successfully wrote 8032 bytes to /tmp/ws/index.html

assistant

Created `/tmp/ws/index.html` — a full-screen boids flocking simulation with: - **Separation, alignment, cohesion** — the three classic flocking rules - **Oriented triangles** — each boid is a teardrop-shaped triangle that points in its movement direction - **Mouse flee** — boids within a radius of your cursor scatter away with strength proportional to proximity - **Smooth steering** — velocity-based movement with speed limits and gradual turning - **Edge avoidance** — soft boundary forces keep boids on screen - **Toroidal wrapping** — boids wrap around edges for continuous space - **Visual polish** — cyan/blue color palette, glow effects, subtle trails, and a faint mouse danger zone indicator Just open the file in a browser and move your mouse to scare the flock!

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

modelkat-coder-air-v2.5
vendorKwaipilot
harnesspi-agent
generated2026-08-01

EVALUATION

4/5 working

Boids flock in cohesive clusters with smooth oriented-triangle steering; a red circle marks cursor but boids don't clearly flee 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 motion36.3%
on click31.7%
on drag34.4%
on wheel36.4%
on enter + space35.0%
on arrow keys35.2%
on w/a/s/d36.9%
frame spread29 / 255
console errors0
js errors none

METRICS

runtime17.9s
tokens in6.2k
tokens out3.3k
cached3.2k
cost / run$0.0025