oneshotlm
Compare all models on this prompt →

Boids flocking · llama-3.3-70b-instruct

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 (2057 bytes)
toolResult

Successfully wrote 2057 bytes to index.html

assistant

The provided code creates 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. The simulation is implemented using HTML, CSS, and JavaScript, and it runs in a sandboxed environment with no network requests. Please note that this code may need to be adjusted based on your specific requirements and the environment in which it will be run. Also, please be aware that the code provided is a basic implementation and might need further optimization and refinement for better performance and visual appeal. If you need further modifications or have any specific questions about the code, feel free to ask.

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

modelllama-3.3-70b-instruct
vendorMeta · Llama
harnesspi-agent
generated2026-08-01

EVALUATION

2/5 working

Small triangular boids drift and rotate on a plain background but appear very sparse and lack visible flocking cohesion.

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 motion0.6%
on click0.3%
on drag0.3%
on wheel0.3%
on enter + space0.3%
on arrow keys0.2%
on w/a/s/d0.1%
frame spread6.6 / 255
console errors0
js errors none

METRICS

runtime22.6s
tokens in4.0k
tokens out832
cached0
cost / run$0.0009