MacroLens - Real-Estate Rent: leaderboard
Metric: Mean absolute percentage error (%; monthly rent predicted from static property attributes for 1,000 held-out U.S. addresses; per-instance APE capped at 1,000%; zero-shot LLM with reasoning disabled). Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 (Non-reasoning) | 22.82 |
| 2 | Qwen 3.5 27B (Non-reasoning) | 24.91 |
| 3 | Llama 4 Scout | 31.3 |
Interactive version: theaggregate.ai/benchmark?slug=macrolens-real-estate-rent · How It Works · Data refreshed daily, snapshot 2026-09-26.