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
Agents' Last Exam v1
Agents
Multimodal
Share
Official website
Professional computer-use tasks, version 1 as labeled by OpenAI. Separate from v1.1 and CLI-only results.
Ranking
Sources
#
Model
Score
1
GPT-6.1 Terra
OpenAI · max
60.0
%
2
GPT-6 Astra
OpenAI · max
59.3
%
2 models total