oneshotlm
Compare all models on this prompt →

Maze generator & solver · qwen3-vl-30b-a3b-instruct

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

I'll create a single-page web app that generates a random maze using the recursive backtracker algorithm and animates a pathfinding solution (BFS) from start to finish.

write index.html (9066 bytes)
toolResult

Successfully wrote 9066 bytes to index.html

assistant

I've created a complete single-page web application that: 1. Generates a random maze using the recursive backtracker algorithm 2. Animates a BFS pathfinding solution from start (top-left) to finish (bottom-right) 3. Includes a button to generate new mazes The implementation includes: - A canvas for rendering the maze and path - Cell-based maze representation with wall management - Recursive backtracker algorithm for maze generation - BFS algorithm for finding the shortest path - Animation of the pathfinding process - Start and end point markers (green and red) The maze is generated with walls between cells, and the solver navigates through open paths by checking if walls exist between adjacent cells. The path is animated step-by-step with a 50ms delay between each step. You can run this HTML file in any modern browser to see the maze generation and pathfinding animation.

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

modelqwen3-vl-30b-a3b-instruct
vendorQwen
harnesspi-agent
generated2026-08-01

EVALUATION

4/5 working

Maze generates and solver animates exploring paths with yellow dots from start to finish, continuing 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 motion0.1%
on click1.2%
on drag2.3%
on wheel0.0%
on enter + space0.0%
on arrow keys0.0%
on w/a/s/d0.0%
frame spread18.7 / 255
console errors0
js errors none

METRICS

runtime25.0s
tokens in5.8k
tokens out3.0k
cached0
cost / run$0.0023