DreamHouse (Planner-Reactive, Facade): leaderboard
Metric: Structural pass rate (x 100): share of generated structures that clear every test of the deterministic validation suite (building-code compliance, physics, geometry, fabrication), on 1,200 DreamHouse residential timber-frame structures (13 architectural styles) per model and protocol, given a multi-view rendering of the finished exterior, which hides the framing, where the model writes one script covering all construction phases in its own order, each phase is checked for load path and stability, and any failure forces a full regeneration; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.5 | 49.4 | #79 |
| 2 | Gemini 3 Flash | 37.6 | #93 |
| 3 | GPT-5 | 24.7 | #91 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=dreamhouse-planner-reactive-facade · How It Works · Data refreshed daily, snapshot 2026-10-11.