Embodied-BenchClaw Aerial-Bench - Interval Selection: leaderboard
Metric: Accuracy (%) on interval selection questions (counts, quantities and depth or scale ranges); 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 2030. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 27B | 44 |
| 2 | Qwen 3.6 35B A3B | 43 |
| 3 | GPT-5.5 | 42 |
| 4 | Kimi K2.5 | 35 |
| 5 | Gemini 3 Pro (Preview) | 33 |
| 6 | Grok 4.20 0309 (Reasoning) | 33 |
| 7 | GPT-5.2 | 32 |
| 8 | Claude Sonnet 4.6 | 31 |
| 9 | Claude Opus 4.7 | 30 |
| 10 | GPT-4.1 | 24 |
| 11 | Claude Haiku 4.5 (20251001) | 24 |
Interactive version: theaggregate.ai/benchmark?slug=embodied-benchclaw-aerial-bench-interval-selection · How It Works · Data refreshed daily, snapshot 2026-09-29.