Glossary
Within-Tool Comparison
Comparing a score against itself over time, inside one engine. The only comparison this site treats as a real signal; comparing raw scores across two different engines is treated as noise.
Definition
A within-tool comparison tracks how a score for one engine changes over time, the same prompt set, the same engine, measured on different dates. This is the comparison this site treats as a real signal.
Comparing one engine's raw score directly against a different engine's raw score is not treated as a finding. Citation behavior varies enormously between engines, published research measured swings of up to several hundred times between engines on the same category, and found only limited overlap between the sources different engines cite for comparable queries, so a cross-engine score comparison is closer to noise than insight.
Same ruler
See how this is measured
This term is part of the same declared methodology every score on this site follows: which prompts, which engines, how many runs.
Related terms
Engine Family
The split between chat engines (ChatGPT, Perplexity, Gemini, Claude) and Search-AI surfaces (Google AI Overviews, AI Mode, Bing Copilot). Never blended into one score.
Share of Answers
The percentage of answers, across a declared prompt set, engine set, and run count, in which a brand was cited. The headline number behind every leaderboard on this site.
Want to see where your own brand stands?
One-time report, no subscription, delivered in days.