AeroGround - Multi-Target Relation: leaderboard

Metric: Accuracy (%; Spatial Understanding: order comparison targets by distance from a reference target; 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 December 2026. 16 models tracked.

Top models

#ModelScore
1Seed 2.0 Pro83.3
2Gemini 3.1 Pro (Preview)78.9
3GPT-5.468.9
4Qwen 3 VL 32B (Thinking)68.9
5Kimi K2.553.3
6Qwen 3 VL 8B (Thinking)52.8
7Qwen 3 VL 32B Instruct51.7
8Qwen 3 VL 8B Instruct49.4

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