Heads up: All models on this page are in their early stages and should be considered placeholders. The underlying methodology is still being refined — take the specific numbers with a grain of salt.
A guided tour of the pitch grading stack
These pages explain what each model measures, how the grades are trained, and how to interpret every score you see in the app.
Location+ measures command. Stuff+ measures physical nastiness on residual xRV after command is removed. Pitching+ brings both signals back together with sequencing and context.
All pitch grade models target xRV. Negative xRV means runs prevented (good for pitchers). Every score is scaled to a 100 mean so higher is always better.
How individual pitch grades add up to a cohesive arsenal.
Next-season outcomes using historical skill signals.
What data powers the models and how features are built.
How we judge model quality and avoid misleading metrics.
Where the models are strong, and where they should be ignored.