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
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 92.67 |
| 2 | Kimi K2.5 | 89.5 |
| 3 | Gemini 3 Pro (Preview) | 89.17 |
| 4 | Qwen 3.6 27B | 86.33 |
| 5 | Claude Sonnet 4.6 | 85.33 |
| 6 | GPT-5.2 | 85.33 |
| 7 | Grok 4.20 0309 (Reasoning) | 85.33 |
| 8 | Claude Opus 4.7 | 85.17 |
| 9 | Qwen 3.6 35B A3B | 84 |
| 10 | GPT-4.1 | 81.67 |
| 11 | Claude 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.