oneshotlm
Compare all models on this prompt →

Brick breaker · mistral-large-2512

Using the pre-provided phaser.min.js (global Phaser), build a playable brick-breaker game with a paddle (arrow keys or mouse), a bouncing ball, and a wall of breakable bricks with a score. Use ONLY procedurally generated graphics via the Phaser Graphics API or generated textures — no external image or audio assets whatsoever.

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

Using the pre-provided phaser.min.js (global Phaser), build a playable brick-breaker game with a paddle (arrow keys or mouse), a bouncing ball, and a wall of breakable bricks with a score. Use ONLY procedurally generated graphics via the Phaser Graphics API or generated textures — no external image or audio assets whatsoever.

assistant
write /tmp/ws/index.html (6154 bytes)
toolResult

Successfully wrote 6154 bytes to /tmp/ws/index.html

assistant

The brick-breaker game is ready! Open `/tmp/ws/index.html` in a browser to play. **How to play:** - Move the paddle with **arrow keys** or **mouse** - Click to start the game - Break all bricks to win - Don't let the ball fall below the paddle The game uses only procedural graphics (no external assets) and runs entirely offline. Enjoy!

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

modelmistral-large-2512
vendorMistral AI
harnesspi-agent
generated2026-08-01

EVALUATION

3/5 working

Functional brick-breaker with paddle, ball, bricks, and score; game ends quickly with GAME OVER but bricks still break and score increases.

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 motion0.0%
on click0.6%
on drag2.3%
on wheel0.3%
on enter + space0.6%
on arrow keys0.6%
on w/a/s/d1.8%
frame spread40.9 / 255
console errors0
js errors none

METRICS

runtime25.5s
tokens in4.7k
tokens out1.8k
cached1.5k
cost / run$0.0044