Benchmark Prompts / P06
Modern house: 12 AI models, one prompt
Every Season 3 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.
12Outputs637 ballots · 16 both-bad
A modern single-story house with flat roof, large windows, and an attached carport.
Every output for this prompt
Click a tile to load the model in 3D, then switch to Wire or X-ray to read the topology. Vote on these blind →
Claude Opus 5.5Modern house Grok 4.7Modern house GPT-6 SolModern house GPT-6 LunaModern house GPT-6.1 SolModern house 3D-AgentModern house GPT-6 AstraModern house Claude Fable 5.1Modern house Claude Opus 5Modern house GPT-5.6 SolModern house Grok 4.6Modern house Claude Fable 5Modern house
Season 3 blind votes for P06
637 ballots · 16 “both bad”
| Competitor | Record | Wins | Losses |
|---|---|---|---|
| Claude Opus 5.5 | 106 | 6 | |
| Grok 4.7 | 80 | 35 | |
| GPT-6.1 Sol | 78 | 3 | |
| GPT-5.6 Sol | 65 | 38 | |
| GPT-6 Sol | 56 | 34 | |
| Claude Fable 5.1 | 51 | 43 | |
| Grok 4.6 | 41 | 60 | |
| Claude Opus 5 | 39 | 54 | |
| GPT-6 Astra | 35 | 91 | |
| 3D-Agent | 33 | 49 | |
| GPT-6 Luna | 14 | 72 | |
| Claude Fable 5 | 2 | 115 |