What are the best Running Shoes, according to AI?

This is the public record for Best Running Shoes: the same questions, every model, every week. We ask each model the real questions buyers ask in this category and record which brands it recommends and in what order. A brand recommended at position i scores 100 × 0.85^(i−1) for that model (#1 = 100, #2 = 85, #3 = 72, …); unmentioned brands score 0.

Each model is ranked independently, so the columns disagree when the models disagree. The consensus score is the mean across the 4models recorded this week, and movement compares against last week’s close.

We report what the models say. We don’t editorialize, and brands can’t pay to change their position.

During the preview period, the rankings shown are simulated sample data while our measurement pipeline comes online. The format, scoring, and methodology are final. The numbers become live once recorded model answers back this category.

What we measure

We measure on the official model APIs: the same question, the same settings, the same week, for every brand. Web search is on, so the models can draw on what is live on the web. Nothing is personalized to a user, which is what makes the columns comparable.

What we don’t

The consumer apps are a different surface. What a person sees inside a chat app can carry memory, personalization, and live experiments on top of the same model, so its answers can differ from the API’s. We do not measure that surface yet. True browser listings, recorded from the consumer apps, arrive with WDIR Ranked, the Pro product. WDIR Ranked · Coming soon

Updated this week · week of 2026-07-06