Embodied-BenchClaw Aerial-Bench - Single Choice: leaderboard
Metric: Accuracy (%) on single-choice selection 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: Around December 2026. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 90 |
| 2 | GPT-5.5 | 89 |
| 3 | Kimi K2.5 | 83 |
| 4 | Claude Opus 4.7 | 82 |
| 5 | Claude Sonnet 4.6 | 79 |
| 6 | Grok 4.20 0309 (Reasoning) | 79 |
| 7 | Qwen 3.6 35B A3B | 78 |
| 8 | Qwen 3.6 27B | 77 |
| 9 | GPT-5.2 | 74 |
| 10 | GPT-4.1 | 68 |
| 11 | Claude Haiku 4.5 (20251001) | 55 |
Interactive version: theaggregate.ai/benchmark?slug=embodied-benchclaw-aerial-bench-single-choice · How It Works · Data refreshed daily, snapshot 2026-09-29.