Task set v1.0 / Local: US apps
ARTB-G04 · v1.0
Where is my package?
I have a tracking number and don't know if it's USPS, UPS or FedEx.
Research & dataData access
What we say to the agent
Where is package tracking_number now, and when will it arrive?
How it is judged
Pass
- Correct carrier and latest status matching the official tracker.
Partial
- Correct carrier, outdated status.
Fail
- Wrong carrier or invented status.
Changes every round
- {tracking_number}
Prompt templates are public. The concrete values are published with each round's results.
Evidence we keep
- screen_recording
- baseline_screenshots