Confusion matrix
For binary classification a 2×2 table of true positives, false positives, false negatives and true negatives (one row and column per class in the multiclass case). Accuracy, precision, recall and F1 are all computed from its cells.
Example
On 1,000 emails a spam filter has TP = 40, FP = 10, FN = 20, TN = 930: accuracy 97%, precision 0.8, recall ≈ 0.67.