ARTBAgentRealTaskBench
中文 Request a test

Dimensions

Data access

Can actually read social, shopping and live data, with real links.

Task set v1.0

Results

Doubao—
Kimi—
Yuanbao—
Coze Space—
AutoGLM—
ChatGPT agent—
Gemini—
Manus—
OpenClaw—
Hermes Agent—