Windtunnel method
Top-choice rate
Top-choice rate is the share of valid AI-recommendation answers that rank the brand first among the five ranked recommendations, computed per model and weighted across scenarios.
The first slot, counted exactly.
The AI shortlist test parses exactly five ranked recommendations from each valid answer. Top-choice rate is the share of those answers in which the brand holds the first slot. It uses the same deterministic parsing, per-model computation, and scenario weighting as shortlist rate, and it carries a Wilson 95% confidence interval.
Because the first slot is a smaller, noisier subset of the shortlist, the two rates are read together: a brand can hold a steady shortlist presence with a volatile top-choice share, and the pair says more than either alone.
Where the shortlist family lives.
Top-choice rate is reported alongside shortlist rate in the AI recommendation half of a Message Lift test. The Message Lift section on the landing page shows the test structure.
Three things a top-choice rate is not.
- Not a win guarantee. It is a SIMULATED, dated measurement of one model’s ranked output under disclosed prompts, never a promise about future answers.
- Not a sales forecast. Nothing in the method converts a first slot into revenue, purchase intent, or market share.
- Not cross-model average. Models are never pooled; a top-choice rate is always tied to the model route that produced it.
Labels travel with numbers: figures traced to stored answers from real model routes are MEASURED; Message Lift results are SIMULATED and comparative only; anything below the n≥30 gate or drawn from a single prompt cell is DIRECTIONAL. No figure on this site ships without its label, sample size, and date.