Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

leaderboard.cn

Benchmark details loading

Loading page content

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Back to benchmarks

OSWorld-VerifiedAgents

Official website

Results for 26 models collected from 12 public sources.

#ModelScore

1

Claude Mythos PreviewAnthropic

85.4%

2

Claude Fable 5Anthropic

85.0%

3

Claude Opus 4.8Anthropic

83.4%

4

Claude Opus 4.7Anthropic

82.8%

5

Claude Sonnet 5Anthropic

81.2%

6

Muse Spark 1.1Meta

80.8%

7

DeepSeek-V4-ProDeepSeek

80.6%

8

GPT-5.5OpenAI

78.7%

9

Claude Sonnet 4.6Anthropic

78.5%

10

Gemini 3.1 ProGoogle

76.2%

26 models total