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

#ModelScore
1Gemma 3 4B (IT)71
2Qwen 3 VL 8B Instruct69.9
3GPT-5 Chat69.7
4Qwen 3 VL 4B Instruct67.9
5InternVL3.5-8B65.2
6DeepSeek V3.263.39
7GPT-4o51.8

Interactive version: theaggregate.ai/benchmark?slug=cvsbench-cvusa-ground-to-satellite · How It Works · Data refreshed daily, snapshot 2026-09-29.