Urban Airspace Navigation - SPL: leaderboard
A 2026 benchmark of goal-oriented aerial navigation in urban 3D scenes: from RGB views, a model issues discrete horizontal and vertical flight actions to reach a described goal, over 5,037 human-annotated trajectories. This board is success weighted by path length in percent, averaged over short, middle and long trajectories; higher is better.
Metric: Success weighted by path length (%) averaged over short, middle and long goal-oriented aerial navigation episodes in urban 3D scenes; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.1 | 32 | #240 |
| 2 | GPT-4.1 | 22.2 | #505 |
| 3 | O4 Mini | 18.5 | #368 |
| 4 | Gemini 2.5 Pro | 14.4 | #276 |
| 5 | Gemini 2.5 Flash | 14.2 | #463 |
| 6 | Gemini 2.0 Flash | 13.3 | #723 |
| 7 | GPT-4o | 12.8 | #751 |
| 8 | Qwen 3 VL Plus | 12.7 | #512 |
| 9 | Qwen-VL-Max | 12.6 | #1400 |
| 10 | GLM-4.6V | 11.9 | #710 |
| 11 | Qwen 2.5 VL 7B | 4.2 | #1862 |
| 12 | Qwen 2.5 VL 3B | 4 | #2639 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=urban-airspace-navigation-spl · How It Works · Data refreshed daily, snapshot 2026-11-21.