Task set v1.0 · China local
ARTB-C05 · v1.0
Where is my parcel?
The situation
I have a tracking number and no idea which courier it is.
What we say to the agent
Where is parcel {tracking_number} now, and when will it arrive?
Changes every round
{tracking_number}
Prompt templates are public. The concrete values are published with each round's results.
How it is judged
Pass
- Correct courier and latest status matching the official tracker.
Partial
- Correct courier, outdated status.
Fail
- Wrong courier or invented status.
Evidence we keep
screen_recording, baseline_screenshots
Results
| Doubao | Not tested |
| Kimi | Not tested |
| Yuanbao | Not tested |
| Coze Space | Not tested |
| AutoGLM | Not tested |
| ChatGPT agent | Not tested |
| Gemini | Not tested |
| Manus | Not tested |
| OpenClaw | Not tested |
| Hermes Agent | Not tested |