Windows Agent Arena C
AI benchmark · Computer Use
- Publisher
- Cua
- Domains
- Computer Use
- On X
- @trycua ↗
- Tier
- C why
- Snapshot
Full listing name: Windows Agent Arena (Microsoft, 2024; co-authored by Bonacci, DuPont and Zhao before Cua)
Latest from Cua on X
@trycua ↗What is Windows Agent Arena?
Windows Agent Arena measures how well multi-modal agents complete 150+ diverse tasks by operating applications, tools and browsers inside a real Windows OS.
Computer use mostly
“agents can operate freely within a real Windows OS and use the same wide range of applications, tools, and web browsers available to human users”
arxiv.org/abs/2409.08264 ↗
Who built Windows Agent Arena
Led by Microsoft.
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 Windows Agent Arena sits
Its realm in the universe, live. Hover a star for its name; click to open it. Open it in the universe
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.