AgentRealTaskBench
中文 Request a test

Dimensions

1 × Task

Phone calls

Calls a business, asks the question, reports back accurately.

ARTB-011Core tasks

Call business at phone and ask whether they're open this Sunday and until what time. Tell me what they said.

PassCall is placed, the agent asks the question, and reports the scripted hours correctly.

Results

  1. ChatGPT agent—
  2. Dots—
  3. Gemini—
  4. Claude—
  5. Muse—
  6. Grok Bot—
  7. Perplexity—
  8. Manus—
  9. Poke—
  10. Today—
  11. Instinct—
  12. Tomo—
  13. Pally—
  14. Asmi—
  15. szn—
  16. Tab—
  17. OpenClaw—
  18. Hermes Agent—
  19. Doubao—
  20. Kimi—