AutomationBench-AA

AutomationBench-AA is Artificial Analysis's independently run version of AutomationBench, covering 657 real-world SaaS workflow tasks across 40 simulated applications (e.g. Gmail, Slack, Salesforce, HubSpot). It scores the share of objectives an agent completes without violating business guardrails, using a private held-out task set.

Released

Unknown

Readiness

Paper only

Primary field

General AI

Benchmark Radar records only publicly supported details and links back to primary sources for verification.