oneshotlm
Compare all models on this prompt →

Windows 95 desktop · qwen-2.5-72b-instruct

Recreate a Windows 95 style desktop in a single page with draggable and closable windows, a Start button and taskbar, desktop icons, and a working clock.

⛨ sandboxed Open in new tab ↗
transcript · 9 messages
user

Recreate a Windows 95 style desktop in a single page with draggable and closable windows, a Start button and taskbar, desktop icons, and a working clock.

assistant
assistant
assistant
write index.html (7325 bytes)
bash {"command":"ls -l index.html","timeout":5}
toolResult

Successfully wrote 7325 bytes to index.html

toolResult

ls: cannot access 'index.html': No such file or directory Command exited with code 2

assistant

It seems there was an issue with the file system. Let me try writing the file again and verifying its existence.

write index.html (7325 bytes)
bash {"command":"ls -l index.html","timeout":5}
toolResult

Successfully wrote 7325 bytes to index.html

toolResult

-rw-r--r--. 1 node node 7325 Aug 1 20:30 index.html

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

modelqwen-2.5-72b-instruct
vendorQwen
harnesspi-agent
generated2026-08-01

EVALUATION

1/5 broken

Only a gray background, taskbar, Start button, and clock render; no icons or windows appear at all.

off-prompt

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 drag0.1%
on wheel0.0%
on enter + space0.0%
on arrow keys0.0%
on w/a/s/d0.0%
frame spread13 / 255
console errors2
js errors none

METRICS

runtime600.0s
tokens in5.9k
tokens out4.4k
cached0
cost / run$0.0039