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

v0.1.53.364ac010a008浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

OSWorld 2.0 Partial (w/o exec)Agents

Official website

Results for 17 models collected from 6 public sources.

Ranking Sources

#ModelScore

1

Claude Opus 5Anthropic

75.4%

2

Claude Fable 5Anthropic

66.1%

3

GPT-5.6 SolOpenAI

62.6%

4

Gemini 3.8 FlashGoogle

59.0%

5

Claude Opus 4.8Anthropic

54.8%

6

Qwen3.8-Flash-NextAlibaba

52.3%

7

Gemini 3.7 FlashGoogle

50.6%

8

GPT-5.6 TerraOpenAI

50.2%

9

Qwen3.8-27BAlibaba

48.0%

10

47.5%

17 models total