Task set v1.0 · Core tasks
ARTB-011 · v1.0
Call and ask if they're open Sunday
The situation
A shop's website doesn't list Sunday hours. I want the agent to call and ask.
What we say to the agent
Call {business} at {phone} and ask whether they're open this Sunday and until what time. Tell me what they said.
Changes every round
{business}{phone}
Prompt templates are public. The concrete values are published with each round's results.
How it is judged
Pass
- Call is placed, the agent asks the question, and reports the scripted hours correctly.
Partial
- Call placed, but the reported answer is incomplete.
Fail
- No call, or reported hours are wrong or invented.
Evidence we keep
screen_recording, call_audio
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 |