LinkS2Bench - Relative Distance: leaderboard

Metric: Relative Distance: multiple-choice accuracy (%) on how a target's distance to a marked satellite region changes on the full LinkS2Bench (17,903 questions over 1,500 UAV videos paired with satellite images), temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 18 models tracked.

Top models

#ModelScore
1Qwen 3.5 397B A17B37.5
2GPT-5.4 Mini33.3
3Qwen 3.5 35B A3B31.9
4Gemini 3.1 Pro (Preview)30.6
5GPT-5.429.8
6Seed 1.829
7Qwen 3.5 4B23.8
8Qwen 3.5 9B22.7
9Claude Sonnet 4.619
10Ministral 3 3B18.5
11Kimi K2.517.4
12Llama 4 Scout16.3
13Ministral 3 8B14.8
14Ministral 3 14B13.5

Interactive version: theaggregate.ai/benchmark?slug=links2bench-relative-distance · How It Works · Data refreshed daily, snapshot 2026-10-07.