HyperAI
Command Palette
Search for a command to run...
AutomationBench-AA
A benchmark measuring agentic task completion across simulated SaaS application environments, scoring the share of each task's objectives completed without guardrail violations.
- Intelligence Index weight
- 5%
- Models
- 150 current, 256 in total
- Median
- 46.0%
- Range
- 0.2%–77.8%