The Brier Score measures how accurate your probability estimates are. It is calculated as the mean squared difference between your stated probability and the actual outcome (0 or 1).
Formula: BS = (p - o)² where p is your stated probability and o is the actual outcome.
A score of 0 is perfect. A score of 0.25 is what you'd get by always saying "50% likely" — the uninformed baseline. Scores below 0.15 are considered skilled. Top forecasters (like those at Good Judgment Project) maintain Brier Scores around 0.10–0.12 over hundreds of predictions.
MindFrame uses Brier Score in calibration challenges to measure not just whether you got the answer right, but whether your confidence matched your accuracy. This trains you to distinguish genuine knowledge from false certainty.