Benchmark Prompts / P04
Mushroom creature: 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.
12Outputs630 ballots · 24 both-bad
A cute cartoon mushroom creature with big eyes and stubby legs, standing.
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 5.5Mushroom creature Grok 4.7Mushroom creature GPT-6 SolMushroom creature GPT-6 LunaMushroom creature GPT-6.1 SolMushroom creature 3D-AgentMushroom creature GPT-6 AstraMushroom creature Claude Fable 5.1Mushroom creature Claude Opus 5Mushroom creature GPT-5.6 SolMushroom creature Grok 4.6Mushroom creature Claude Fable 5Mushroom creature
Season 3 blind votes for P04
630 ballots · 24 “both bad”
| Competitor | Record | Wins | Losses |
|---|---|---|---|
| Claude Opus 5.5 | 99 | 6 | |
| GPT-6 Astra | 75 | 31 | |
| 3D-Agent | 67 | 31 | |
| Claude Fable 5.1 | 60 | 36 | |
| GPT-6 Sol | 53 | 20 | |
| GPT-6.1 Sol | 53 | 23 | |
| Claude Opus 5 | 51 | 60 | |
| GPT-6 Luna | 42 | 38 | |
| Grok 4.7 | 36 | 74 | |
| GPT-5.6 Sol | 25 | 81 | |
| Claude Fable 5 | 16 | 76 | |
| Grok 4.6 | 2 | 103 |