oneshotlm
Compare all models on this prompt →

2048 · muse-spark-1.2

Build a playable 2048 game with arrow-key tile sliding and merging, smooth animations, a score, and win and lose states.

⛨ sandboxed Open in new tab ↗
transcript · 6 messages
user

Build a playable 2048 game with arrow-key tile sliding and merging, smooth animations, a score, and win and lose states.

assistant
write index.html (19330 bytes)
toolResult

Successfully wrote 19330 bytes to index.html

assistant
bash {"command":"ls -lh index.html && grep -c \"tile\" index.html && head -5 index.html"}
toolResult

-rw-r--r--. 1 node node 19K Aug 13 01:27 index.html 53 <!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width,initial-scale=1,maximum-scale=1">

assistant

Playable 2048 built in **index.html** (single file, offline, no CDNs). **Features:** - 4×4 grid with smooth `left/top` slide transitions + `appear`/`pop` merge animations - Arrow keys / WASD / HJKL + swipe & mouse-drag + on-screen D-pad - Correct 2048 merge logic (one merge per tile per move, chain handling e.g. `[2,2,2,2]→[4,4]`) - Random 2 (90%) / 4 (10%) spawns, score with `+N` pop, Best score via `localStorage` - **Win** overlay at 2048 (Keep going / New Game), **Lose** overlay when no moves remain - Undo (Z / button), New Game (R / button), responsive layout

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

modelmuse-spark-1.2
vendorMeta
harnesspi-agent
generated2026-08-13

EVALUATION

4/5 working

2048 game responds correctly to arrow keys and WASD, tiles merge and slide, score tracked, clean UI.

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 click0.0%
on drag0.0%
on wheel3.8%
on enter + space25.0%
on arrow keys4.0%
on w/a/s/d6.5%
frame spread26.7 / 255
console errors0
js errors none

METRICS

runtime40.7s
tokens in17k
tokens out9.1k
cached11k
cost / run$0.0479