Benchmark Prompts / P08
Sailing boat: 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.
12Outputs671 ballots · 8 both-bad
A small sailing boat with hull, single mast, boom, and simplified sail.
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 5.5Sailing boat Grok 4.7Sailing boat GPT-6 SolSailing boat GPT-6 LunaSailing boat GPT-6.1 SolSailing boat 3D-AgentSailing boat GPT-6 AstraSailing boat Claude Fable 5.1Sailing boat Claude Opus 5Sailing boat GPT-5.6 SolSailing boat Grok 4.6Sailing boat Claude Fable 5Sailing boat
Season 3 blind votes for P08
671 ballots · 8 “both bad”
| Competitor | Record | Wins | Losses |
|---|---|---|---|
| Claude Opus 5.5 | 109 | 11 | |
| 3D-Agent | 93 | 32 | |
| GPT-6 Astra | 76 | 36 | |
| GPT-6.1 Sol | 64 | 9 | |
| Claude Opus 5 | 56 | 39 | |
| Grok 4.7 | 55 | 59 | |
| Grok 4.6 | 51 | 54 | |
| GPT-6 Sol | 49 | 44 | |
| GPT-5.6 Sol | 42 | 67 | |
| Claude Fable 5.1 | 29 | 92 | |
| GPT-6 Luna | 22 | 82 | |
| Claude Fable 5 | 0 | 121 |