Urban Airspace Navigation - Success Rate: 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 the success rate in percent averaged over short, middle and long trajectories; higher is better.

Metric: Success rate (%) averaged over short, middle and long goal-oriented aerial navigation episodes in urban 3D scenes (5,037 samples), the model choosing discrete 3D actions from RGB views; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5.134#240
2GPT-4.124.3#505
3O4 Mini20.2#368
4Gemini 2.5 Pro16.3#276
5Gemini 2.5 Flash14.9#463
6GPT-4o14.7#751
7Gemini 2.0 Flash14.7#723
8Qwen-VL-Max13#1400
9Qwen 3 VL Plus12.9#512
10GLM-4.6V12#710
11Qwen 2.5 VL 7B4.5#1862
12Qwen 2.5 VL 3B4.2#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-success-rate · How It Works · Data refreshed daily, snapshot 2026-11-21.