Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Benchmark details loading
Back to benchmarks
OSWorld 2.1 (offline, OpenAI)
Agents
Multimodal
Share
Official website
OpenAI's OSWorld 2.1 offline-set result. The release does not specify partial versus strict scoring or task count; kept separate from explicitly defined variants.
Ranking
Sources
#
Model
Score
1
GPT-6 Astra
OpenAI · max; offline set; partial/strict scoring not specified
80.9
%
2
GPT-6.1 Terra
OpenAI · max; offline set; partial/strict scoring not specified
74.2
%
2 models total