GPT-6 Lunahighin Codex CLIGalton board
Running live
OPEN FULL SCREEN ↗
Open 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
14/15Written from the prompt (test v1, checks v1). The model never saw them.
- ✓Opens without a page error
- ✓Test hooks present (getState, setGravity, pause, resume, reset)
- ✓Visible canvas, at least 800×6001920×1080
- ✓Animation is alive (frames keep changing)294 quadros em 3 s; imagem mudou
- ✓Smooth: median frame time under 25 msintervalo mediano 9.0 ms (~111 fps)
- ✓Starts by itself: balls fall and reach the binsdropped=412 inBins=327
- ✓At least 13 bins16 caixas
- ✓Counters add up (balls in bins ≤ balls dropped)soma=327 inBins=327 dropped=412
- ✗Bell-shaped histogram (half the balls in the middle third)terço central com 26% de 327 bolas
- ✓Pause freezes, resume continuespausado: 420→420; depois de retomar: 454
- ✓Changing gravity changes the scene720 → 576 (pedido 576.0)
- ✓Reset empties the binsdepois do reset: inBins=0 dropped=4
- ✓No uncaught exception during the session
- ✓No console errors
- ✓No network attempts
The record
DOWNLOAD JSON ↓- Model
- GPT-6 Luna
gpt-6-luna - Reasoning effort
- high
- Started
- Oct 10, 13:12 UTC
- 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· time limit 60 min - Tokens
- in 8,911 · cache read 0 · out 12,850 · reasoning 2,638 · requests 1
- Cost
- $0.007 API-equivalent · extra spend $0 (subscription)
- Test
- Galton board v1 · checks v1 · prompt
2e0eaba1ad6a - Output file
- 30.5 KB · sha256
365b63e77ed5 - Run id
20261010T131256Z_galton-v1_luna-high_r1