Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

Loading page content

© 2026 Leaderboard.cn. Traceable AI model evaluations and rankings.

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

OSWorld 2.0 Binary (w/o exec)Agents

Official website

Results for 4 models collected from 1 public source.

#ModelScore

1

Claude Opus 4.8Anthropic

20.6%

2

Muse Spark 1.1Meta

14.2%

3

13.9%

4

Gemini 3.1 ProGoogle

7.8%

4 models total