Blueprint-Bench — leaderboard
Tests spatial reasoning by asking models to convert ~20 apartment photographs into accurate 2D floor plans. Most models perform at or below the random baseline (0.279); humans score 0.547.
Metric: Similarity Score. Source: andonlabs.com. Status: saturation imminent. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 0.43 |
| 2 | Gemini 2.5 Pro | 0.42 |
| 3 | GPT-5 Mini | 0.4 |
| 4 | Grok 4 | 0.39 |
| 5 | Gemini 2.5 Flash | 0.36 |
| 6 | Claude Opus 4 | 0.29 |
| 7 | Claude Sonnet 4 | 0.27 |
| 8 | GPT-4o | 0.13 |
Interactive version: theaggregate.ai/benchmark?slug=blueprint-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.