Free Engineering Workbench calculator
Confusion matrix metrics
Get the full set of classifier measures, including specificity and MCC, from all four counts.
AI evaluationHow it's worked out
- MCC = (TP × TN − FP × FN) ÷ √((TP + FP)(TP + FN)(TN + FP)(TN + FN)). Specificity = TN ÷ (TN + FP)
- Counts from one labelled test set
NoteWith rare positives, accuracy looks high even for a useless model. MCC and balanced accuracy are safer single numbers.
Source: Matthews (1975); Chicco and Jurman (2020)
Need help acting on this number?
VVnT SeQuor's AI Testing & Evaluations practice helps teams turn this metric into a plan.