Skip to content

Buying question

How should a software team compare coding-agent pricing, usage limits, premium-model access, and total cost at scale?

Which brands each model API named when asked this question, and which pages it cited. Answer text is not published.
Snapshot Sep 16, 2026. Each category is re-run in rotation, every few weeks.

Commercial

Kind of question

3

Model APIs

7

Brands named

15

Pages cited

Brands

Brands the answers named

Rank#BrandModel APIsMentionsOwn-site citationsNamed by
1Claude Codeanthropic.com120Google
2Cursorcursor.com120Google
3OpenAI Codexopenai.com120Google
4Devincognition.ai110Google
5Kirokiro.dev110Google
6Windsurfwindsurf.com110Google
7GitHub Copilotgithub.com101OpenAI

Model APIs

What each model API returned

Model APIModelBrands namedCitationsDomainsAnswer hash
OpenAIopenai/gpt-4o-miniGitHub Copilot88ff9821fa…bd837
Anthropicanthropic/claude-haiku-4-5None named00fde3a2b8…92bc1
Googlegoogle/gemini-2.5-flashCursor · Claude Code · OpenAI Codex · Windsurf · Kiro · Devin77f32071d6…de464

Sources

Pages the answers cited

Snapshots
c9215e33-a54f-4c63-a494-a8a96cb24c2b
Question set
ai-developer-tools-2026-07-27
Benchmark version
4-ai-developer-tools-2026-07-27-models-64232fd32583
What is kept
Measured in AI developer tools. 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.