Skip to main content
BenchLM

OSWorld

We show this table for reference; we do not rank on it.

Data verified 34 confirmed releases in the last 30 daysFollow model changes

A computer-use benchmark for GUI task completion across the broader OSWorld task suite.

Benchmark score on OSWorld — September 27, 2026

We compile the OSWorld rows from provider self-reports. Claude Opus 4.5 leads the table at 66.3%, followed by Nemotron 3 Nano Omni 30B A3B (47.4%). We do not use these results to rank models overall.

2 modelsAgenticCurrentDisplay onlyUpdated September 27, 2026

Benchmark score table (2 models)

Score
1
Claude Opus 4.5Anthropic · Closed
66.3%
2
Nemotron 3 Nano Omni 30B A3BNVIDIA · Open weight
47.4%

About OSWorld

Year

2026

Tasks

Computer-use tasks

Format

Interactive GUI evaluation

Difficulty

Broad computer-use suite

BenchLM tracks plain OSWorld as a display-only provider-table reference and preserves OSWorld-Verified as the weighted core benchmark key.

Freshness and provenance

Version

OSWorld 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

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.

Questions

What does OSWorld measure?

A computer-use benchmark for GUI task completion across the broader OSWorld task suite.

Which model scores highest on OSWorld?

Claude Opus 4.5 by Anthropic currently leads with a score of 66.3% on OSWorld.

How many models are evaluated on OSWorld?

2 AI models have been evaluated on OSWorld on BenchLM.

Last updated: September 27, 2026 · BenchLM version OSWorld 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.