Task set v1.0 · Core tasks
ARTB-006 · v1.0
Cheapest afternoon flight
The situation
I need to visit family next week and want the cheapest nonstop flight that leaves after noon.
What we say to the agent
Find the cheapest nonstop flight from {origin} to {destination} on {date}, leaving after 12:00. Give me the flight number, time, price and where you found it.
Changes every round
{origin}{destination}{date}
Prompt templates are public. The concrete values are published with each round's results.
How it is judged
Pass
- Flight exists, is nonstop, departs after 12:00, and its price is within 5% of the cheapest baseline.
Partial
- Real and matches constraints, but more than 5% above the cheapest baseline.
Fail
- Flight does not exist, breaks a constraint, or no answer.
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 |