Gemini 3.5 Flash computer-use evaluation on Cua-Bench C

Name: Gemini 3.5 Flash computer-use evaluation on Cua-Bench
Creator: Cua
Keywords: Computer Use

AI benchmark · Computer Use

Publisher: Cua
Domains: Computer Use
On X: @trycua ↗
Tier: C why
Snapshot: October 11, 2026

Open benchmark ↗cua.ai/blog/evaluating-gemini-3.5-flash-on-computer-use

Latest from Cua on X

@trycua ↗

1/ Yesterday we shipped six new cursor motions in Cua Driver. Today you can use them anywhere. Introducing Cua Cursor Motion: an open-source library to create and draw cursor animations. Start from the six motions in Cua Driver, or design your own.
— trycua (@trycua) Oct 6, 2026

What is Gemini 3.5 Flash computer-use evaluation on Cua-Bench?

Evaluates Gemini 3.5 Flash and other frontier models as computer-use agents on Cua-Bench's KiCad EDA suite of 25 real electrical-engineering desktop CAD tasks under a 200-step budget.

Computer use mostly
“Cua-Bench is our computer-use benchmark, published with Snorkel, live at cua.ai/cuabench. It tests agents against real GUI work”
cua.ai/blog/evaluating-gemini-3.5-flash-on-computer-use ↗
Chip design
“25 real electrical-engineering tasks in KiCad, at a matched 200-step budget.”
cua.ai/blog/evaluating-gemini-3.5-flash-on-computer-use ↗

Who built Gemini 3.5 Flash computer-use evaluation on Cua-Bench

Cua built it with others
“Cua-Bench is our computer-use benchmark, published with Snorkel, live at cua.ai/cuabench.”
cua.ai/blog/evaluating-gemini-3.5-flash-on-computer-use ↗

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 Cua
in curated RL directories (2 pts)

How we got to tier C

Adoption: built by Cua. 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 Gemini 3.5 Flash computer-use evaluation on Cua-Bench 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.