Statistics & Probability

Instant, private, and free

Confusion Matrix Calculator.

Calculate binary classification metrics from a confusion matrix.

On-device calculationNo signup
01

Set your values

Results update as you type.

Accuracy: 0.85

Accuracy

0.850000
Precision: 0.888889

Precision

0.888889
Recall: 0.8

Recall

0.800000
Specificity: 0.9

Specificity

0.900000
F1 score: 0.842105

F1 score

0.842105

Results update automatically as you type.

Use Cases

Evaluate a classification model

Quickly assess the performance of a machine learning model by entering the counts from its test set predictions.

Example: After running a spam filter, enter TP=85, TN=900, FP=10, FN=5 to see its accuracy and F1 score.

Compare model performance

Use the calculator to compare different models or threshold settings by entering their respective confusion matrices.

Example: Enter the confusion matrix for two models and compare their precision and recall side by side.

Frequently Asked Questions

What is a confusion matrix?
A confusion matrix is a table used to evaluate the performance of a classification model. It shows the counts of true positives, true negatives, false positives, and false negatives, which are the building blocks for metrics like accuracy, precision, recall, and F1 score.
How do I use this calculator?
Enter the counts for true positives, true negatives, false positives, and false negatives in the respective fields. The calculator instantly computes the derived metrics using standard formulas, updating as you type.
What metrics does this calculator compute?
Based on the four input values, it calculates accuracy, precision, recall (sensitivity), specificity, F1 score, and other common classification metrics. The exact set is derived from the standard formulas for these metrics.

Tips & Common Mistakes

Tips

  • Double-check that your counts are correct: true positives are correctly predicted positives, and false positives are incorrectly predicted positives.
  • Use the debounced results to see metrics update as you type, but ensure all four fields are filled for accurate calculations.
  • Remember that accuracy can be misleading with imbalanced datasets; consider precision and recall as well.
  • This calculator is for reference; always validate with your own analysis for critical decisions.

Common Mistakes to Avoid

  • Confusing false positives with false negatives: false positives are actual negatives predicted as positive, while false negatives are actual positives predicted as negative.
  • Entering percentages instead of raw counts: the calculator expects actual counts, not proportions.
  • Forgetting to fill all four fields, which can lead to incomplete or incorrect metric calculations.

Last updated: August 13, 2026