oneshotlm
Compare all models on this prompt →

Maze generator & solver · glm-5.3

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
thinking
Build a self-contained maze app: canvas rendering, recursive backtracker, then A* animation with visualization.
write index.html (13469 bytes)
toolResult

Successfully wrote 13469 bytes to index.html

assistant

Done — `index.html` contains a fully self-contained maze app. **Features:** - **Generation:** Recursive-backtracker (iterative DFS) carves the maze, animated with a moving green "head" and trail; 5 maze sizes (15×15 to 61×61) - **Solvers:** - **A\***: picks the open node with the lowest `f = g + h` (Manhattan heuristic) - **BFS**: plain FIFO frontier expansion - **Animation:** visited cells (indigo), frontier (cyan), then the final path reveals cell-by-cell in gold, with a stats readout (path length, nodes explored) - **Controls:** algorithm selector, maze size, solver speed slider, New Maze / Solve buttons Open `index.html` in any browser — no network or external resources needed.

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

modelglm-5.3
vendorZ.ai · GLM
harnesspi-agent
generated2026-08-27

EVALUATION

3/5 partial

Maze generates and animates, click regenerates maze, but solver never visibly runs; arrows/wasd/drag/wheel 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 motion1.5%
on click37.3%
on drag0.0%
on wheel0.0%
on enter + space18.2%
on arrow keys0.0%
on w/a/s/d0.0%
frame spread16 / 255
console errors0
js errors none

METRICS

runtime43.3s
tokens in7.1k
tokens out4.3k
cached2.8k
cost / run$0.0258