HuzzleWorld computer-use models C

Name: HuzzleWorld computer-use models
Creator: Huzzle Labs
Keywords: Coding,Computer Use,Enterprise Workflows,Long-Horizon,Private Codebases

AI benchmark · Coding

Publisher: Huzzle Labs
Domains: Coding Computer Use Enterprise Workflows Long-Horizon Private Codebases
On X: @huzzle_labs ↗
Tier: C why
Snapshot: October 11, 2026

Open benchmark ↗labs.huzzle.com/huzzle-world

Full listing name: HuzzleWorld computer-use models: self-reported 72.4% on ScreenSpot-Pro (3B) and 58.6% on OSWorld-Verified (8B), leaderboard snapshot 2026-09-17

Latest from Huzzle Labs on X

@huzzle_labs ↗

thanks for the shout out! @deedydas
— huzzle_labs (@huzzle_labs) Jul 13, 2026
We open-sourced two RL environments on OpenEnv - Phantom Grid (visual memory) and Spreadsheet (stateful editing). Live on HuggingFace as Docker Spaces. We built these because most agent benchmarks only test one-shot retrieval. They don't tell you if an agent can carry state across steps, recover mid-task, or edit a workbook without silently breaking a downstream sheet. RL researchers need environments that actually test that, and right now there aren't many. Both use OpenEnv's reset/step/state interface, so they plug straight into existing training pipelines. Blog:
— huzzle_labs (@huzzle_labs) Apr 9, 2026

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 Huzzle Labs
in curated RL directories (2 pts)

How we got to tier C

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

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

Not on the map yet: no line from its own site or paper places it in a domain.

More Coding AI benchmarks

Coding RL environments

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