Skip to main content

OSWorld-Verified

A verified subset of OSWorld focused on computer-use tasks in desktop-like environments, including navigation, editing, and workflow completion.

Top models on OSWorld-Verified — April 29, 2026

As of April 29, 2026, Holo3-35B-A3B leads the OSWorld-Verified leaderboard with 82.6% , followed by Claude Mythos Preview (79.6%) and Holo3-122B-A10B (78.8%).

18 modelsAgentic24% of category scoreCurrentUpdated April 29, 2026

According to BenchLM.ai, Holo3-35B-A3B leads the OSWorld-Verified benchmark with a score of 82.6%, followed by Claude Mythos Preview (79.6%) and Holo3-122B-A10B (78.8%). The scores show moderate spread, with meaningful differences between the top tier and mid-tier models.

18 models have been evaluated on OSWorld-Verified. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. Within that category, OSWorld-Verified contributes 24% of the category score, so strong performance here directly affects a model's overall ranking.

About OSWorld-Verified

Year

2025

Tasks

Desktop and GUI tasks

Format

Interactive computer-use evaluation

Difficulty

Complex multi-step workflows

OSWorld-Verified measures whether models can operate software interfaces, keep state across steps, and complete practical GUI workflows. It is one of the clearest public signals for computer-use capability.

BenchLM freshness & provenance

Version

OSWorld Verified

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

Current

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Leaderboard (18 models)

1
82.6%
2
79.6%
3
78.8%
4
78.7%
5
78%
6
75%
7
73.1%
8
72.7%
9
72.1%
10
72.1%
11
66.3%
12
64.7%
13
61.4%
14
58%
15
56.2%
16
54.5%
17
47.3%
18
39%

FAQ

What does OSWorld-Verified measure?

A verified subset of OSWorld focused on computer-use tasks in desktop-like environments, including navigation, editing, and workflow completion.

Which model scores highest on OSWorld-Verified?

Holo3-35B-A3B by H Company currently leads with a score of 82.6% on OSWorld-Verified.

How many models are evaluated on OSWorld-Verified?

18 AI models have been evaluated on OSWorld-Verified on BenchLM.

Last updated: April 29, 2026 · BenchLM version OSWorld Verified

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.