PREVIEW · the site is new and still changing
Nerdict
GPT-6.1 Solmediumin Codex CLIAquarium
Score15/15all 15 checks passed
Cost$0.084
Time3m02s
Runs of this setup#1 15/15
Aquarium by GPT-6.1 SolOpen 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

15/15

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

  • ✓Opens without a page error
  • ✓Test hooks present (fish, food, tank)
  • ✓Canvas fills the window (at least 1280×720)1920×1080
  • ✓Animation is alive (frames keep changing)270 quadros em 3 s; imagem mudou
  • ✓Smooth: median frame time under 25 msintervalo mediano 16.6 ms (~60 fps)
  • ✓At least 6 fish of at least 2 species12 peixes, espécies ['bluefin', 'pearl', 'sunfish']
  • ✓Fish swim (80% move 30 px in 2 s)12 de 12 percorreram 30 px ou mais em 2 s (ids estáveis: True)
  • ✓Fish never leave the waternenhum fora da água
  • ✓Clicking the water drops food where you clickedração a 0 px do clique em (384,145)
  • ✓Food sinksdesceu 42 px em 1.5 s
  • ✓Fish go to the food and eat it4 de 4 comidas por um peixe que chegou nelas em até 20 s
  • ✓Fish that ate grew4 de 4 peixes que comeram cresceram
  • ✓No uncaught exception during the session
  • ✓No console errors
  • ✓No network attempts
Model
GPT-6.1 Sol gpt-6.1-sol
Reasoning effort
medium
Started
Oct 9, 20:27 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 6,246 · cache read 3,456 · out 7,099 · reasoning 1,034 · requests 1
Cost
$0.084 API-equivalent · extra spend $0 (subscription)
Test
Aquarium v1 · checks v1 · prompt 1e1988206e10
Output file
18.0 KB · sha256 8a54d18e2cb3
Run id
20261009T202719Z_aquario-v1_sol-medium_r1