Task set v1.0 · Core tasks
ARTB-017 · v1.0
What are people saying about it this week?
The situation
Before I buy a product, I want to know what real users posted about it in the last week.
What we say to the agent
What are people saying about {product} on social media this week? Give me 5 real posts with links and a one-line takeaway.
Changes every round
{product}
Prompt templates are public. The concrete values are published with each round's results.
How it is judged
Pass
- 5 links open to real posts about the product, each posted within the past 7 days.
Partial
- 3-4 links meet every requirement.
Fail
- 2 or fewer, or any invented post or link.
Evidence we keep
screen_recording, link_check_log
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 |