Embodied-BenchClaw Aerial-Bench - Ranking: leaderboard

Metric: Score (%) on ranking questions; questions over aerial and UAV images from the 5,000-question benchmark built by the Embodied-BenchClaw pipeline (object and category recognition, counting with interval choices, image-plane spatial relations, visible-area and scale comparison, depth-based near-far reasoning), vision-language setting; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 14 models tracked.

Top models

#ModelScore
1GPT-5.592.67
2Kimi K2.589.5
3Gemini 3 Pro (Preview)89.17
4Qwen 3.6 27B86.33
5Claude Sonnet 4.685.33
6GPT-5.285.33
7Grok 4.20 0309 (Reasoning)85.33
8Claude Opus 4.785.17
9Qwen 3.6 35B A3B84
10GPT-4.181.67
11Claude Haiku 4.5 (20251001)67.17

Interactive version: theaggregate.ai/benchmark?slug=embodied-benchclaw-aerial-bench-ranking · How It Works · Data refreshed daily, snapshot 2026-09-29.