Computing & Software

Binary Prediction AUC & Brier Score Calculator

Compare ranking discrimination with probability error using paired labels and predicted probabilities.

How the calculation works

ROC AUC with average ranks for ties = classifier_auc(labels,probabilities) AUC. Mean Brier score = brier_score(labels,probabilities) mean squared probability error.

Worked example

Example inputs — Actual class labels: 0 or 1: 1, 0, 1, 0; Predicted probability of class 1, in matching order: .9, .8, .4, .1. Expected results — ROC AUC with average ranks for ties: 0.75 AUC; Mean Brier score: 0.255 mean squared probability error.

Assumptions and limits

Analytical software/hardware scenario, not a benchmark or a live provider quote. Use the actual architecture, workload and billing definitions; overheads not named in the model are excluded. Requires both actual classes and probabilities in [0,1]. AUC evaluates ranking, while Brier score includes calibration error; neither substitutes for validation on representative unseen data.

Reference and further reading

Read the underlying subject reference. Calculith is an independent implementation; the reference does not endorse or certify this tool.

Related calculators

Browse all 1000 calculators →

Example values are editable. Results are estimates where assumptions apply. Calculations run in your browser. Updated 2026-11-16.