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

v0.1.66.c14ade6abf77浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

OSWorld 2.0 (2026-08-08 offline, partial)MultimodalAgents

Official website

Results for 6 models collected from 4 public sources.

Ranking Sources

#ModelScore

1

GPT-6 AstraOpenAI · max

73.5%

2

GPT-6.1 SolOpenAI · max

71.4%

3

Claude Opus 5Anthropic

70.2%

4

Gemini 4 ArgonGoogle

69.2%

5

GPT-5.6 SolOpenAI

65.7%

6

GPT-6 SolOpenAI · max

64.4%

6 models total