Benchmark Prompts / P11
Spiral staircase: 7 AI models, one prompt
Every Season 1 competitor received this prompt verbatim, at default settings, with one generation and no manual cleanup. Nothing below is cherry-picked — the failures ship too, because a benchmark that hides them isn't one.
The prompt (v1.0, CC BY 4.0)
A spiral staircase with twelve steps winding around a central column, with a handrail.
What it tests: Parametric/procedural reasoning: counted repetition, rotation, and precision.
Category: Abstract
Blind vote results for P11
85 ballots · 6 “both bad”
| Competitor | Wins | Losses |
|---|---|---|
| Claude Fable 5 | 16 | 7 |
| Claude Opus 5 | 15 | 6 |
| GPT-5.6 Sol | 15 | 5 |
| Claude Opus 4.8 | 13 | 14 |
| Grok 4.6 | 7 | 0 |
| Claude Sonnet 5 | 6 | 14 |
| Claude Haiku 4.5 | 0 | 26 |
Every output for this prompt
Click any card to load the model in 3D and orbit it. Generation notes under each entry state exactly how it was produced.
P11: “A spiral staircase with twelve steps winding around a central column, with a handrail.”
P11: “A spiral staircase with twelve steps winding around a central column, with a handrail.”
P11: “A spiral staircase with twelve steps winding around a central column, with a handrail.”
P11: “A spiral staircase with twelve steps winding around a central column, with a handrail.”
P11: “A spiral staircase with twelve steps winding around a central column, with a handrail.”
P11: “A spiral staircase with twelve steps winding around a central column, with a handrail.”
P11: “A spiral staircase with twelve steps winding around a central column, with a handrail.”