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
AutomationBench v1.0.6 (Private)
Agents
Share
Official website
AutomationBench v1.0.6 private held-out evaluation: strict task pass rate across business workflows. Separate from the public 600-task set and results with an unspecified version.
Ranking
Sources
#
Model
Score
1
GPT-6 Sol
OpenAI · xhigh
33.2
%
2
GPT-6 Astra
OpenAI · low
30.3
%
2 models total