ELSS - Landing Site Filtering (Nanjing): leaderboard

Metric: F1 (%; the model judges each candidate landing site in a remote-sensing image patch Safe or Unsafe, scored against human suitability labels of 100 semantic-segmentation recommendations; Nanjing satellite imagery, 63 suitable sites). Source: arxiv.org. Saturation forecast: Around December 2026. 5 models tracked.

Top models

#ModelScore
1Grok 4.2083.2
2GPT-5.482.5
3Seed 2.0 Pro77.2
4Gemini 3.1 Pro (Preview)72.9
5Claude Opus 4.672.1

Interactive version: theaggregate.ai/benchmark?slug=elss-landing-site-filtering-nanjing · How It Works · Data refreshed daily, snapshot 2026-09-26.