oneshotlm
Compare all models on this prompt →

Boids flocking · gpt-5.6-sol

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
thinking
**Creating a polished index**

I'm thinking about creating an index, and I want it to look polished and full-screen. I guess that means using a canvas and possibly adding some controls, like sliders and a pause/reset option. It sounds like I should request a simulation to see how it works. I need to make sure everything is self-contained, so I'll focus on writing a complete file for this project. Let's get started!
write /tmp/ws/index.html (11959 bytes)
toolResult

Successfully wrote 11959 bytes to /tmp/ws/index.html

assistant

Created the full-screen interactive boid flocking simulation in: `/tmp/ws/index.html` Features include separation, alignment, cohesion, smooth steering, cursor avoidance, adjustable parameters, pause/resume, re-seeding, and responsive full-screen rendering.

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

modelgpt-5.6-sol
vendorOpenAI
harnesspi-agent
generated2026-08-03

EVALUATION

4/5 working

Boid flocking simulation with idle animation, mouse click/drag/wheel disrupts flock, and Space pauses simulation; arrows/WASD have no effect.

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 motion8.1%
on click8.3%
on drag7.7%
on wheel7.8%
on enter + space6.6%
on arrow keys0.0%
on w/a/s/d0.0%
frame spread13 / 255
console errors0
js errors none

METRICS

runtime51.0s
tokens in6.6k
tokens out4.4k
cached2.3k
cost / run$0.1600