ARTBAgentRealTaskBench
中文 Request a test

Dimensions

Proactive help

Shows up at the right time without being asked again.

Task set v1.0

Results

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