CVSBench - CVUSA Ground-to-Satellite: leaderboard
Metric: Accuracy (%) on CVUSA-subset ground-to-satellite questions: from a street-view image, infer spatial attributes of the unseen satellite view; four-choice and binary-choice questions over paired street-view and satellite images (Gemini-2.5-flash-generated, human-verified), test split; higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 3 4B (IT) | 71 |
| 2 | Qwen 3 VL 8B Instruct | 69.9 |
| 3 | GPT-5 Chat | 69.7 |
| 4 | Qwen 3 VL 4B Instruct | 67.9 |
| 5 | InternVL3.5-8B | 65.2 |
| 6 | DeepSeek V3.2 | 63.39 |
| 7 | GPT-4o | 51.8 |
Interactive version: theaggregate.ai/benchmark?slug=cvsbench-cvusa-ground-to-satellite · How It Works · Data refreshed daily, snapshot 2026-09-29.