The F1 Score is the harmonic mean of Precision and Recall, used to comprehensively evaluate a model's accuracy and coverage in identifying positive classes. The formula is 2×(P×R)/(P+R). It is more robust than simple accuracy for imbalanced datasets and is one of the most commonly used comprehensive metrics for classification, extraction, and detection tasks. It is typically reported as a percentage or a score between 0 and 1, where higher values are better.