Skip to content
VibeCodeBench

VS ·Notebook Mini-Golf

Opus 5.5 vs Sonnet 5.5 vs Fable 5.1Names hidden. Which is which?

Three Claude models made the same doodled mini-golf game. Putt through each one.

Is it fair?

A fair match: same effort, same kind of tool.

  • Same effort
  • Agents only

All three ran at high effort as Claude Code subagents, with the same prompt pasted as is. A workflow restart ran this prompt twice, so each run has 2 tries on record; the first try worked every time and is the one shown.

What these mean
Same effort
Every run used the same step on the shared effort ladder.
Agents only
All runs used coding agents.

Each run

  • AnthropicOpus 5.5Effort: High, level 3 of 5works · try 1 of 2Receipt and tries
  • AnthropicSonnet 5.5Effort: High, level 3 of 5works · try 1 of 2Receipt and tries
  • AnthropicFable 5.1Effort: High, level 3 of 5works · try 1 of 2Receipt and tries

The benchmark

Nine holes of slingshot mini-golf doodled on notebook paper.

Try this: Drag back from the ball like a slingshot, let go.

I keep the exact prompts private for now. See it in the gallery.

Make your own comparison

More comparisons