oneshotlm
Compare all models on this prompt →

Maze generator & solver · gpt-4.1-mini

Generate a random maze with the recursive-backtracker algorithm on a canvas, then animate an A-star or BFS solver finding the path from start to finish.

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

Generate a random maze with the recursive-backtracker algorithm on a canvas, then animate an A-star or BFS solver finding the path from start to finish.

assistant
write index.html (5590 bytes)
toolResult

Successfully wrote 5590 bytes to index.html

assistant

I have created a self-contained single HTML file named index.html which generates a random maze using the recursive backtracker algorithm on a canvas, then animates a BFS solver finding the path from start (top-left) to finish (bottom-right). Click the canvas to generate and solve a new maze. Would you like me to display the code?

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-4.1-mini
vendorOpenAI
harnesspi-agent
generated2026-08-01

EVALUATION

4/5 working

Maze generation and A*/BFS solver animate correctly with visited (blue) and frontier/path (yellow) cells, progressing over time regardless of input.

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 motion0.7%
on click21.2%
on drag8.4%
on wheel24.3%
on enter + space7.7%
on arrow keys5.8%
on w/a/s/d4.6%
frame spread51.7 / 255
console errors0
js errors none

METRICS

runtime27.6s
tokens in4.2k
tokens out1.9k
cached1.0k
cost / run$0.0044