Skip to content

Buying question

Create a reproducible AI customer agent benchmark covering resolution, accuracy, policy compliance, actions, escalation, latency, and customer effort.

Which brands each model API named when asked this question, and which pages it cited. Answer text is not published.
Snapshot Oct 10, 2026. Each category is re-run in rotation, every few weeks.

Commercial

Kind of question

3

Model APIs

1

Brands named

8

Pages cited

Brands

Brands the answers named

Rank#BrandModel APIsMentionsOwn-site citationsNamed by
1Intercom Finintercom.com101OpenAI

Model APIs

What each model API returned

Model APIModelBrands namedCitationsDomainsAnswer hash
OpenAIopenai/gpt-4o-miniIntercom Fin77c389ac3f…d4c6f
Anthropicanthropic/claude-haiku-4-5None named00463f2cbe…b2892
Googlegoogle/gemini-2.5-flashNone named11129fb472…aa042

Sources

Pages the answers cited

Snapshots
b2abc10b-7b96-481f-906f-1e140feb8e0b
Question set
ai-customer-agent-platforms-2026-07-27
Benchmark version
4-ai-customer-agent-platforms-2026-07-27-models-64232fd32583
What is kept
Measured in Service agents. Full answers are not stored or published, and no customer data is included.

Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.

  • Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
  • Who gets namedEvery competitor in the answers, most named first.
  • The pages AI readsThe sources behind each answer.
  • Three fixesWhat to fix first, with a brief for the first article.