Embodied-BenchClaw Aerial-Bench - Binary Comparison: leaderboard
Metric: Accuracy (%) on binary comparison 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 | Kimi K2.5 | 95 |
| 2 | Qwen 3.6 27B | 94 |
| 3 | GPT-5.5 | 93 |
| 4 | Gemini 3 Pro (Preview) | 93 |
| 5 | Grok 4.20 0309 (Reasoning) | 91 |
| 6 | Qwen 3.6 35B A3B | 87 |
| 7 | Claude Sonnet 4.6 | 85 |
| 8 | GPT-5.2 | 85 |
| 9 | Claude Opus 4.7 | 83 |
| 10 | GPT-4.1 | 79 |
| 11 | Claude Haiku 4.5 (20251001) | 67 |
Interactive version: theaggregate.ai/benchmark?slug=embodied-benchclaw-aerial-bench-binary-comparison · How It Works · Data refreshed daily, snapshot 2026-09-29.