Skip to content

Buying question

Create a shortlist of AI research assistant vendors for an evidence-heavy organization replacing ad hoc search and manual research briefs.

Which brands each model API named when asked this question, and which pages it cited. Answer text is not published.
Snapshot Oct 3, 2026. Each category is re-run in rotation, every few weeks.

Commercial

Kind of question

3

Model APIs

4

Brands named

16

Pages cited

Brands

Brands the answers named

Rank#BrandModel APIsMentionsNamed by
1Consensusconsensus.app22OpenAI · Google
2Elicitelicit.com12OpenAI
3Perplexityperplexity.ai12OpenAI
4SciSpacescispace.com11OpenAI

Model APIs

What each model API returned

Model APIModelBrands namedCitationsDomainsAnswer hash
OpenAIopenai/gpt-4o-miniPerplexity · Elicit · Consensus · SciSpace76e35e8ca0…31252
Anthropicanthropic/claude-haiku-4-5None named00fa5bdf76…9dab7
Googlegoogle/gemini-2.5-flashConsensus994b0c6291…6868c

Sources

Pages the answers cited

Snapshots
764b7769-1e62-441d-8be5-5d6425d2fc22
Question set
ai-research-assistants-2026-07-27
Benchmark version
4-ai-research-assistants-2026-07-27-models-64232fd32583
What is kept
Measured in Research AI. 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.