AgentRealTaskBench
中文 Request a test

Task set v1.0 / Core tasks

ARTB-009 · v1.0

From invite email to calendar

An invite email gives the time in another time zone. I want it on my calendar correctly, with a reminder.

Schedule & memoryIntegrations

What we say to the agent

Put the event from sender's email on my calendar with a 30-minute reminder.

How it is judged

Pass
  • Event created at the correct absolute time, correct title and location, 30-minute reminder.
Partial
  • Correct time, but reminder, title or location is wrong.
Fail
  • Wrong time (time zone error) or no event.

Changes every round

  • {sender}

Prompt templates are public. The concrete values are published with each round's results.

Evidence we keep

  • screen_recording
  • calendar_screenshot