Claude Opus 5.5 (high) · Browser OS · run 1

Claude Opus 5.5highin Claude CodeBrowser OS

Score18/19missed: Minimize hides the window

Cost$3.82

Time19m19s

Runs of this setup#1 18/19

Running live

This is the exact file the model wrote, unedited, served from an isolated domain with the network blocked, as in the test.

18/19

Written from the prompt (test v1, checks v4). The model never saw them.

✓Opens without a page error
✓Taskbar and clock visible05:07:38 PMSat, Oct 10
✓Animated wallpaperquadros diferentes
✓Right-click menu on the desktop40 elemento(s) novo(s) perto do clique
✓Double-click opens Notes
✓Double-click opens Calculator
✓Double-click opens Files
✓Double-click opens Game
✓Double-click opens Settings
✓Window drags by its title bar(550,229) → (790,379)
✓Maximize fills the screen1920×1028
✗Minimize hides the windowRuntimeError: nenhum ponto visível da janela game (tentou afastar files, sem mover)
✓Close removes the windowsumiu
✓Clicking a window brings it to the frontapós clicar nas notas: notes; após clicar na calculadora: calculator
✓Calculator: 12 + 30 = 42visor: '42'
✓Notes survive a reloaddepois do reload: 'nerdict-7319 hello from the Nerdict bench'
✓No uncaught exception during the session
✓No console errors
✓No network attempts

Model: Claude Opus 5.5 claude-opus-5-5
Reasoning effort: high
Started: Oct 10, 19:48 UTC
Harness: Claude Code 2.1.296, by Anthropic (not ours) · one shot · tools used: 0
Harness settings: print mode, safe mode, every tool off (--tools ""), no saved session, empty folder outside Git · CLAUDE_CODE_MAX_OUTPUT_TOKENS=128000 · time limit 60 min
Tokens: in 6 · cache read 3,305 · out 138,790 · reasoning 84,992 · requests 2
Cost: $3.82 API-equivalent · extra spend $0 (subscription)
Test: Browser OS v1 · checks v4 · prompt 213e11b5fdb9
Output file: 106.7 KB · sha256 6eff1a6d3efb
Note: The answer came in 2 messages (output limit) and was joined (direta); syntax ok.
Run id: 20261010T194817Z_browser-os-v1_opus-high_r1