LinkS2Bench - Region Interaction: leaderboard
LinkS2Bench (LinkS²Bench, 2026) task on drone videos paired with satellite imagery: multiple-choice accuracy (%) on whether a target engages with a marked satellite region; higher is better.
Metric: Region Interaction: multiple-choice accuracy (%) on whether a target engages with a marked satellite region 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 November 2027. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 57.3 | #102 |
| 2 | Qwen 3.5 397B A17B | 55.1 | #270 |
| 3 | Gemini-3.1-Flash [LinkS2Bench checkpoint unspecified] | 54.7 | |
| 4 | Claude Sonnet 4.6 | 54 | #179 |
| 5 | Seed 1.8 | 50.3 | #258 |
| 6 | GPT-5.4 | 50.1 | #138 |
| 7 | GLM-4.6V-Flash | 50 | #1049 |
| 8 | Qwen 3.5 9B | 48.5 | #838 |
| 9 | LLaVA-OneVision-1.5-4B | 47.5 | #1874 |
| 10 | Qwen 3.5 35B A3B | 46.8 | #494 |
| 11 | GPT-5.4 Mini | 44.7 | #409 |
| 12 | Kimi K2.5 | 43.8 | #272 |
| 13 | Ministral 3 14B | 41.4 | #1885 |
| 14 | LLaVA-OneVision-1.5-8B | 40 | #1876 |
| 15 | Ministral 3 8B | 37.5 | #2166 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=links2bench-region-interaction · How It Works · Data refreshed daily, snapshot 2026-11-22.