Benchmark Prompts / P09
Potted plant: 11 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.
11Outputs567 ballots · 9 both-bad
A potted plant: terracotta pot with a leafy monstera-style plant, about six large leaves.
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 5.5Potted plant Grok 4.7Potted plant GPT-6 SolPotted plant GPT-6 LunaPotted plant GPT-6.1 SolPotted plant 3D-AgentPotted plant GPT-6 AstraPotted plant Claude Fable 5.1Potted plant Claude Opus 5Potted plant GPT-5.6 SolPotted plant Claude Fable 5Potted plant
Season 3 blind votes for P09
567 ballots · 9 “both bad”
| Competitor | Record | Wins | Losses |
|---|---|---|---|
| Claude Opus 5.5 | 112 | 8 | |
| 3D-Agent | 84 | 31 | |
| GPT-6 Astra | 79 | 23 | |
| Claude Opus 5 | 74 | 24 | |
| Claude Fable 5.1 | 59 | 39 | |
| GPT-6 Sol | 44 | 45 | |
| GPT-5.6 Sol | 30 | 63 | |
| GPT-6 Luna | 26 | 68 | |
| Grok 4.7 | 21 | 60 | |
| Claude Fable 5 | 4 | 110 | |
| GPT-6.1 Sol | 2 | 64 |