Research note 007

Why model versions matter in AI visibility research

“ChatGPT” is not one fixed system. Models, retrieval modes and interfaces change continuously. An observation means little without knowing what produced it.

What should be recorded

  • Provider — OpenAI, Google, Anthropic, Perplexity or other.
  • Model — The model identity returned by the provider, where available.
  • Date and time — When the observation was collected.
  • Retrieval status — Whether web search or retrieval was used.
  • Prompt and context — Exact prompt text and any location or language context.

Why “a ChatGPT result” is not enough

Two observations labelled “ChatGPT” may come from different models with different retrieval behaviour. Comparing them as if they were the same system can attribute a model change to a change in the firm's visibility. FirmRanker reports results per system and treats model changes as a variable to track over time.

FirmRanker is an international research and intelligence platform studying how AI systems discover, surface, cite and recommend law firms.

One ecosystem. Three ways to help your firm.

Measure with FirmRanker. Understand with Law By Dan. Act with Practice Proof.

FirmRanker: Measure

Find out whether AI includes your firm in your local market, wherever you are based. Start with a free check, then explore the research behind the answers.

Check your firm free

Law By Dan: Understand

Make sense of the shift in legal discovery. Read Dan Toombs’ analysis and follow The Future Client briefing.

Read Dan’s analysis

Practice Proof: Act

Put the findings to work. Get help with your firm’s positioning, reputation, content, search and technology.

Talk to Practice Proof

Follow The Future Client, Dan Toombs’ free weekly briefing for law-firm leaders.

Get The Future Client

Implementation services are separate from research. Being a Practice Proof client does not influence FirmRanker findings.