Precision, Recall, and F1

Also known as: precision, recall, F1 score

Precision measures the fraction of a model's positive predictions that are correct; recall measures the fraction of actual positives the model successfully identifies. F1 is the harmonic mean of the two, balancing both concerns. In NLP evaluation, token-level F1 is a standard metric for extractive QA and named entity recognition tasks where partial matches matter, while precision and recall individually matter when the cost of false positives and false negatives differ greatly.