Skip to content
VibeCodeBench

VS

Same prompt. You pick the AIs.

Two? Drag to compare. Three to six? A grid. Then play each one.

Pick 2 to 6 runs

Names hidden. To change the runs, show the names.

Claude Fable 5.2 · High: a still of the demo
Claude Haiku 5.5 · High: a still of the demo
Claude Fable 5.2 · HighClaude Haiku 5.5 · High

Drag to compare

Anthropicworks · auto-checked (Checked by an automated pass. Not hand-played yet.)API estimate · about $1.86
Anthropicworks · auto-checked (Checked by an automated pass. Not hand-played yet.)API estimate · under $0.01

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

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

Saved

Ready-made comparisons