PREVIEW · the site is new and still changing
Nerdict
Claude Haiku 5.5highin Claude CodeGalton board
Score14/15missed: Bell-shaped histogram (half the balls in the middle third)
Cost$0.037
Time5m13s
Runs of this setup#1 15/15#2 14/15#3 14/15
Galton board by Claude Haiku 5.5Open 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

14/15

Written 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 800×6001620×1080
  • ✓Animation is alive (frames keep changing)369 quadros em 3 s; imagem mudou
  • ✓Smooth: median frame time under 25 msintervalo mediano 8.3 ms (~120 fps)
  • ✓Starts by itself: balls fall and reach the binsdropped=506 inBins=434
  • ✓At least 13 bins15 caixas
  • ✓Counters add up (balls in bins ≤ balls dropped)soma=434 inBins=434 dropped=506
  • ✗Bell-shaped histogram (half the balls in the middle third)terço central com 31% de 434 bolas
  • ✓Pause freezes, resume continuespausado: 509→509; depois de retomar: 554
  • ✓Changing gravity changes the scene900 → 720 (pedido 720.0)
  • ✓Reset empties the binsdepois do reset: inBins=0 dropped=5
  • ✓No uncaught exception during the session
  • ✓No console errors
  • ✓No network attempts
Model
Claude Haiku 5.5 claude-haiku-5-5
Reasoning effort
high
Started
Oct 10, 00:46 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
Tokens
in 2 · cache read 3,007 · out 74,001 · reasoning 62,560 · requests 1
Cost
$0.037 API-equivalent · extra spend $0 (subscription)
Test
Galton board v1 · checks v1 · prompt 2e0eaba1ad6a
Output file
22.4 KB · sha256 3d09ce6a8a6e
Run id
20261010T004603Z_galton-v1_haiku-high_r3