SpatialUAV - Aerial-Ground Collaboration Recognition: leaderboard
Aerial-ground view matching from SpatialUAV (Zhang et al., 2026): the model matches a drone view with the ground-level view of the same place, or the reverse, among clean candidate images. Accuracy in percent over 500 questions; higher is better.
Metric: Collaboration Recognition Accuracy (%; choose the aerial or ground view that matches a given view). Source: arxiv.org. Saturation forecast: Around February 2027. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 80.4 | #75 |
| 2 | GPT-5.4 | 79.8 | #121 |
| 3 | Qwen 3.6 27B | 58.2 | #339 |
| 4 | Qwen 3.5 9B | 37 | #803 |
| 5 | Qwen 3.6 35B A3B | 34.8 | #461 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=spatialuav-aerial-ground-collaboration-recognition · How It Works · Data refreshed daily, snapshot 2026-11-12.