SpatialQuery-1M - Proximity Decision: leaderboard
Metric: Accuracy (%; binary decision whether the closest same-category instance lies within a distance threshold of the reference object, 5,000 fixed queries, 1,000 per threshold of 0.5, 1.0, 1.5, 2.0 and 3.0 m with balanced labels; black-image sanity filter: a query earns credit only when the model returns valid outputs for both the original RGB image and a same-size uniform black image, is correct on the original and incorrect on the black image; invalid outputs score zero; zero-shot, identical decoding settings). Source: arxiv.org. Saturation forecast: Around December 2026. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 65.24 |
| 2 | GPT-4o | 60.26 |
| 3 | GPT-4o Mini | 54.46 |
| 4 | Gemini 2.5 Flash | 52.52 |
| 5 | Qwen 2.5 VL 7B | 41.62 |
Interactive version: theaggregate.ai/benchmark?slug=spatialquery-1m-proximity-decision · How It Works · Data refreshed daily, snapshot 2026-09-29.