← Benchmarks
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.
id automationbench-aa · max 1 · 1 models reported
| # | Model | Score |
|---|
No scores for this benchmark yet.