Skip to main content

OSWorld 2.0

A long-horizon computer-use benchmark covering realistic workflows across everyday and professional desktop tasks.

Data verified

Benchmark score on OSWorld 2.0 — July 9, 2026

BenchLM mirrors the published score view for OSWorld 2.0. Claude Opus 4.8 leads the public snapshot at 20.6% , followed by Claude Opus 4.7 (Adaptive) (18.2%) and Muse Spark 1.1 (14.2%). BenchLM does not use these results to rank models overall.

9 modelsAgenticCurrentDisplay onlyUpdated July 9, 2026

The published OSWorld 2.0 snapshot is tightly clustered at the top: Claude Opus 4.8 sits at 20.6%, while the third row is only 6.4 points behind. The broader top-10 spread is 17.8 points, so the benchmark still separates strong models even when the leaders cluster.

9 models have been evaluated on OSWorld 2.0. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. OSWorld 2.0 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About OSWorld 2.0

Year

2026

Tasks

108 long-horizon computer-use workflows

Format

Interactive computer-use evaluation

Difficulty

Long-horizon professional workflows

OSWorld 2.0 expands computer-use evaluation to 108 long-horizon workflows that require state tracking, cross-source reasoning, visual-spatial precision, dynamic interaction, and verification. BenchLM stores the primary binary-completion score as a display-only agentic benchmark.

BenchLM freshness & provenance

Version

OSWorld 2.0 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.

Benchmark score table (9 models)

1
Claude Opus 4.8claude-opus-4-8
20.6%
2
Claude Opus 4.7 (Adaptive)claude-opus-4-7-max
18.2%
3
Muse Spark 1.1muse-spark-1-1
14.2%
4
Claude Opus 4.7claude-opus-4-7
13.9%
5
GPT-5.5gpt-5-5
13.0%
6
Claude Sonnet 4.6claude-sonnet-4-6
8.3%
7
Kimi K2.6kimi-2-6
4.6%
8
MiniMax M3minimax-m3
4.6%
9
Qwen3.7 Plusqwen3-7-plus
2.8%

FAQ

What does OSWorld 2.0 measure?

A long-horizon computer-use benchmark covering realistic workflows across everyday and professional desktop tasks.

Which model scores highest on OSWorld 2.0?

Claude Opus 4.8 by Anthropic currently leads with a score of 20.6% on OSWorld 2.0.

How many models are evaluated on OSWorld 2.0?

9 AI models have been evaluated on OSWorld 2.0 on BenchLM.

Last updated: July 9, 2026 · BenchLM version OSWorld 2.0 2026

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.