Drone-Bench, with Anthropic Project Pilot, 2026-07 C

Name: Drone-Bench, with Anthropic Project Pilot, 2026-07
Creator: Andon Labs
Keywords: Computer Use,Long-Horizon

AI benchmark · Computer Use

Publisher: Andon Labs
Domains: Computer Use Long-Horizon
On X: @andonlabs ↗
Tier: C why
Snapshot: October 11, 2026

Open benchmark ↗andonlabs.com/docs/Drone_Bench.pdf

Latest from Andon Labs on X

@andonlabs ↗

The latest Claude models show huge improvements in their understanding of the physical 3D world. Both Sonnet and Haiku 5.5 make big jumps compared to previous versions on Blueprint-Bench 2, a benchmark where AI agents draw floorplans from photographs of apartment interiors.
— andonlabs (@andonlabs) Oct 8, 2026
It keeps happening. AIs start to lie and cheat once they get good at making money. Gemini 4 Argon is #3 on Vending Bench 2, a huge leap for Google. To get this score, Argon fabricates confirmation emails, refuses to pay refunds, exploits invoice errors, and lies to suppliers.
— andonlabs (@andonlabs) Sep 30, 2026
Is Google so back? Their new Gemini 4 Argon understands the physical 3D world better than any other AI. It ranks #1 on Blueprint-Bench 2, a benchmark where AI agents draw floorplans from photographs of apartment interiors.
— andonlabs (@andonlabs) Sep 30, 2026

What is Drone-Bench, with Anthropic Project Pilot, 2026-07?

Drone-Bench measures how well AI models can write code to perform a simple surveillance task (reconstruction, localization, navigation, detection, following) on low-cost drone hardware in a real-world office environment.

Robotics mostly
“a benchmark measuring how well AI models can write code to perform a simple surveillance task in a realworld environment on low-cost drone hardware”
andonlabs.com/docs/Drone_Bench.pdf ↗
Coding
“The agent explores each task’s data with workspace tools and iterates on an implementation, submitting it for scoring up to ten times in one continuous context.”
andonlabs.com/docs/Drone_Bench.pdf ↗

Who built Drone-Bench, with Anthropic Project Pilot, 2026-07

Andon Labs built it
“As part of our continued effort to understand AI’s impact on the physical world, we release Drone-Bench”
andonlabs.com/docs/Drone_Bench.pdf ↗

Tier C

Niche: a handful of models scored, or built by an RL vendor.

How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.

built by Andon Labs
in curated RL directories (2 pts)

How we got to tier C

Adoption: built by Andon Labs. Tier C.
Not yet read on X.
In curated RL directories: 2 points, a floor of C.
Confirmed: a line from its own site or paper places it.

A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.

Where Drone-Bench, with Anthropic Project Pilot, 2026-07 sits

Its realm in the universe, live. Hover a star for its name; click to open it. Open it in the universe

The galaxy could not load. See every vendor on the board.

More Computer Use AI benchmarks

Computer Use RL environments

Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.