PREVIEW · the site is new and still changing
Nerdict
GPT-6 Lunamaxin Codex CLIBrowser OS
Score7/19missed: Double-click opens Notes · Double-click opens Calculator · +10 more
Cost$0.015
Time3m20s
Runs of this setup#1 18/19#2 7/19#3 19/19
Browser OS by GPT-6 LunaOpen it running ↗

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

What the robot did

The comparison clip (the same script for every model)

Checks

7/19

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

  • ✓Opens without a page error
  • ✓Taskbar and clock visible10:32 AM Sat, Oct 10
  • ✓Animated wallpaperquadros diferentes
  • ✓Right-click menu on the desktop5 elemento(s) novo(s) perto do clique
  • ✗Double-click opens Notesjanela não apareceu
  • ✗Double-click opens Calculatorjanela não apareceu
  • ✗Double-click opens Filesjanela não apareceu
  • ✗Double-click opens Gamejanela não apareceu
  • ✗Double-click opens Settingsjanela não apareceu
  • ✗Window drags by its title barRuntimeError: nenhum ponto visível da janela notes
  • ✗Maximize fills the screenRuntimeError: nenhum ponto visível da janela files
  • ✗Minimize hides the windowRuntimeError: nenhum ponto visível da janela game
  • ✗Close removes the windowRuntimeError: nenhum ponto visível da janela settings
  • ✗Clicking a window brings it to the frontRuntimeError: nenhum ponto visível da janela calculator
  • ✗Calculator: 12 + 30 = 42RuntimeError: nenhum ponto visível da janela calculator
  • ✗Notes survive a reloadRuntimeError: nenhum ponto visível da janela notes
  • ✓No uncaught exception during the session
  • ✓No console errors
  • ✓No network attempts
Model
GPT-6 Luna gpt-6-luna
Reasoning effort
max
Started
Oct 9, 20:01 UTC
Harness
Codex CLI 0.162.0, by OpenAI (not ours) · one shot · tools used: 0
Harness settings
isolated container with no global instructions, read-only sandbox; shell, browser, apps, multi-agent and web off; empty /work folder · imagem=nerdict-bancada-codex:0.162.0 · sandbox=read-only
Tokens
in 9,042 · cache read 0 · out 28,868 · reasoning 5,921 · requests 1
Cost
$0.015 API-equivalent · extra spend $0 (subscription)
Test
Browser OS v1 · checks v4 · prompt 213e11b5fdb9
Output file
74.7 KB · sha256 ae0a859f6dff
Run id
20261009T200130Z_browser-os-v1_luna-max_r2