Description

A comprehensive benchmark suite that measures how well frontier AI models can autonomously write code for complex drone tasks, including 3D reconstruction, localization, navigation, detection, and following. It tracks the progress of models like GPT-6 Astra and Claude Fable 5.1 against a human-written baseline for real-world surveillance on low-cost hardware.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.