Benchmark Prompts / P07
Pickup truck: 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.
12Outputs639 ballots · 23 both-bad
A low-poly pickup truck with visible wheels, cabin, and cargo bed, game-asset style.
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 5.5Pickup truck Grok 4.7Pickup truck GPT-6 SolPickup truck GPT-6 LunaPickup truck GPT-6.1 SolPickup truck 3D-AgentPickup truck GPT-6 AstraPickup truck Claude Fable 5.1Pickup truck Claude Opus 5Pickup truck GPT-5.6 SolPickup truck Grok 4.6Pickup truck Claude Fable 5Pickup truck
Season 3 blind votes for P07
639 ballots · 23 “both bad”
| Competitor | Record | Wins | Losses |
|---|---|---|---|
| Claude Opus 5.5 | 100 | 17 | |
| 3D-Agent | 84 | 27 | |
| GPT-6.1 Sol | 75 | 3 | |
| GPT-5.6 Sol | 63 | 36 | |
| Claude Opus 5 | 54 | 44 | |
| GPT-6 Luna | 54 | 24 | |
| GPT-6 Astra | 42 | 48 | |
| GPT-6 Sol | 38 | 35 | |
| Grok 4.6 | 32 | 79 | |
| Claude Fable 5.1 | 20 | 89 | |
| Grok 4.7 | 19 | 87 | |
| Claude Fable 5 | 7 | 99 |