EarthSpatialBench (Direct) - Within Binary Classification: leaderboard
Metric: Macro-averaged F1 (%) on EarthSpatialBench yes/no containment (within) questions on 512x512 SatlasPretrain Earth images at about 1 m resolution, direct prompting; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 91 | #145 |
| 2 | GPT-5 | 85 | #91 |
| 3 | Qwen 3 VL 30B A3B Instruct | 71 | #365 |
| 4 | Claude 3.5 Sonnet | 68 | #337 |
| 5 | Qwen 3 VL 30B A3B (Thinking) | 68 | #338 (Qwen 3 VL 30B A3B) |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=earthspatialbench-direct-within-binary-classification · How It Works · Data refreshed daily, snapshot 2026-10-11.