Skip to content

Observatory · Comparison

ChatGPT vs Claude: same questions, different sources

On identical buying questions, Claude takes 87.8% of its cited sources from rankings and comparison pages, against 57.0% for ChatGPT. Data: 5,174 answers per engine from two tracked projects, July 12 to October 11, 2026.

Updated

57% / 88%

rankings among sources (ChatGPT / Claude)

96% / 84%

answers citing sources (ChatGPT / Claude)

4.3 / 3.8

sources per answer (ChatGPT / Claude)

Rankings among sources
ChatGPT57%Claude88%
Answers citing sources
ChatGPT96%Claude84%
Sources per answer
ChatGPT4.3Claude3.8
Same questions asked to both engines : 5,174 answers per engine, Peec AI, July 12, 2026 to October 11, 2026.
ChatGPTClaude
Rankings among sources57%88%
Answers citing sources96%84%
Sources per answer4.33.8

This comparison puts the same buying questions to ChatGPT and Claude: 5,174 answers per engine, from two projects tracked by Archipel in Peec AI, mostly in French.

ChatGPT cites a source more often: 96.4% of answers against 83.7% for Claude. It also cites slightly more sources: 4.3 per answer against 3.8. The real difference is what they cite. Rankings and comparisons make up 87.8% of Claude sources, against 57.0% for ChatGPT.

Read the numbers with care: two projects is a narrow base, and ChatGPT's ranking share here (57.0%) is higher than across the full Observatory (28.5%, Profound data), because the questions differ. Duels use Peec AI data: identical questions asked to both engines over the same period. Figures can differ from the engine pages, which use larger Profound samples.

Practical consequence: a brand absent from the rankings of its category can still appear in ChatGPT through its own site, but almost never in Claude.

Method

406,626 AI answers collected every day from July 12, 2026 to October 11, 2026 on over 1,700 purchase-intent questions tracked by Archipel (mostly in French, plus the United States and the Netherlands). ChatGPT, Google AI Overviews, Perplexity and Copilot: Profound data. Claude and Gemini: Peec AI data. Sources are classified automatically from their address and title. Figures are aggregated: no brand or client is published. Free to reuse with a link to this page.

FAQ

Frequently asked questions

Does Claude cite more rankings than ChatGPT?
Yes, on identical buying questions Claude takes 87.8% of its sources from rankings and comparisons, against 57.0% for ChatGPT, based on 5,174 answers per engine.
Which cites sources more often, ChatGPT or Claude?
ChatGPT cites sources more often than Claude: 96.4% of answers against 83.7%, on identical buying questions tracked by Archipel.
How many sources do ChatGPT and Claude cite per answer?
On identical questions, ChatGPT cites 4.3 sources per answer and Claude 3.8.
How reliable is the ChatGPT vs Claude comparison?
The ChatGPT vs Claude comparison rests on 5,174 answers per engine from two tracked projects, a narrow base. The direction is consistent with the full Claude data (88.1% rankings).

Shall we get started?

Free GEO audit: your rank on ChatGPT, Claude and Google AI Overviews, your competitors and your first actions. Reply within half a business day.