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 Partial (w/o exec)Agents

Official website

Results for 7 models collected from 2 public sources.

#ModelScore

1

GPT-5.6 SolOpenAI

62.6%

2

Claude Opus 4.8Anthropic

54.8%

3

GPT-5.6 TerraOpenAI

50.2%

4

47.5%

5

Muse Spark 1.1Meta

47.3%

6

GPT-5.6 LunaOpenAI

45.6%

7

Gemini 3.1 ProGoogle

30.6%

7 models total