AeroGround - Region Counting: leaderboard

Metric: Accuracy (%; Spatial Understanding: count category instances inside a marked aerial region; aerial-ground collaborative questions from paired simulated UAV and ground views, exact-match scoring of the parsed option or mapping, invalid output scored wrong; one deterministic run). Source: arxiv.org. Saturation forecast: Around 2033. 16 models tracked.

Top models

#ModelScore
1Qwen 3 VL 32B (Thinking)45.3
2GPT-5.439.1
3Qwen 3 VL 8B (Thinking)39.1
4Kimi K2.537.5
5Qwen 3 VL 8B Instruct34.4
6Qwen 3 VL 32B Instruct34.4
7Gemini 3.1 Pro (Preview)23.4
8Seed 2.0 Pro20.3

Interactive version: theaggregate.ai/benchmark?slug=aeroground-region-counting · How It Works · Data refreshed daily, snapshot 2026-09-26.