DroneCATS (Approaching): leaderboard
A multimodal model dropped straight into a drone's control loop with its entire action space declared in the prompt, told to fly to a described target. This is the approach task's success rate, and the ceiling is 65 percent — the frontier can see where to go far more reliably than it can get there.
Metric: Success Rate (%). Source: arxiv.org. Saturation forecast: Around May 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.7 Flash | 65 | #23 |
| 2 | GPT-5 | 60 | #98 |
| 3 | Qwen 3.5 9B | 35 | #379 |
| 4 | Claude Opus 5 | 35 | #12 |
| 5 | Qwen 3.5 27B | 25 | #187 |
| 6 | Qwen 3.5 4B | 15 | #475 |
| 7 | Qwen 3.5 2B | 0 | #1148 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=dronecats-approaching · How It Works · Data refreshed daily, snapshot 2026-10-20.