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

#ModelScore
1Qwen 3.6 27B44
2Qwen 3.6 35B A3B43
3GPT-5.542
4Kimi K2.535
5Gemini 3 Pro (Preview)33
6Grok 4.20 0309 (Reasoning)33
7GPT-5.232
8Claude Sonnet 4.631
9Claude Opus 4.730
10GPT-4.124
11Claude 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.