Precision Recall Calculator

Calculate precision, recall, F1 score, accuracy, and specificity from confusion matrix values. Free online machine learning evaluation metrics calculator.

📊

Precision Recall Calculator

Enter your confusion matrix values (TP, FP, FN, TN) to instantly calculate precision, recall, F1 score, accuracy, specificity, and more. All calculations run locally in your browser.

Confusion Matrix

True Positive (TP)

Correctly predicted positive

False Negative (FN)

Missed positive (Type II)

False Positive (FP)

Wrong positive (Type I)

True Negative (TN)

Correctly predicted negative

Total samples1,000

Ctrl+Enter to recalculate

Confusion Matrix

9.0%

1.5%

1.0%

885

88.5%

← Predicted Pos | Predicted Neg →

Example Scenarios

Key Metrics

90.00%

Precision

85.71%

Recall

87.80%

F1 Score

Accuracy97.50%

Specificity98.88%

Precision

90.00%

Of all predicted positives, how many were correct?

Recall

85.71%

Of all actual positives, how many were detected?

F1 Score

87.80%

Harmonic mean of precision and recall.

Accuracy

97.50%

Fraction of all predictions that were correct.

Specificity

98.88%

Of all actual negatives, how many were correctly identified?

NPV

98.33%

Negative Predictive Value — accuracy of negative predictions.

FPR

1.12%

False Positive Rate (1 − Specificity).

FNR

14.29%

False Negative Rate (1 − Recall).

MCC

0.8644

Matthews Correlation Coefficient (−1 to +1).

Metrics Overview

Precision90.00%

Recall85.71%

F1 Score87.80%

Accuracy97.50%

Specificity98.88%

How the Precision Recall Calculator Works

This tool computes the core classification evaluation metrics used in machine learning and AI: precision, recall, F1 score, accuracy, and specificity — directly from the four values of a binary confusion matrix (TP, FP, FN, TN). All calculations run instantly in your browser with no data uploaded.

Enter your confusion matrix values and every metric updates in real time. Toggle the formula panel to see the step-by-step calculation for each metric.

The Confusion Matrix

	Predicted Positive	Predicted Negative
Actual Positive	TP True Positive	FN False Negative
Actual Negative	FP False Positive	TN True Negative

TP (True Positive): Model correctly predicted Positive
FP (False Positive): Model predicted Positive, but actual was Negative (Type I error)
FN (False Negative): Model predicted Negative, but actual was Positive (Type II error)
TN (True Negative): Model correctly predicted Negative

All Formulas

Precision    = TP ÷ (TP + FP)
Recall       = TP ÷ (TP + FN)        [also called Sensitivity]
F1 Score     = 2 × (Precision × Recall) ÷ (Precision + Recall)
Accuracy     = (TP + TN) ÷ (TP + FP + FN + TN)
Specificity  = TN ÷ (TN + FP)        [also called True Negative Rate]
NPV          = TN ÷ (TN + FN)        [Negative Predictive Value]
FPR          = FP ÷ (FP + TN)        [False Positive Rate = 1 - Specificity]
FNR          = FN ÷ (FN + TP)        [False Negative Rate = 1 - Recall]
MCC          = (TP×TN − FP×FN) ÷ √((TP+FP)(TP+FN)(TN+FP)(TN+FN))

Metric Reference Guide

Metric	Answers	Best used when
Precision	Of all positive predictions, how many were correct?	False positives are costly (e.g. spam filter)
Recall	Of all actual positives, how many were found?	False negatives are costly (e.g. cancer screening)
F1 Score	Balanced trade-off between precision and recall	Imbalanced datasets where both FP and FN matter
Accuracy	Of all predictions, how many were correct?	Balanced datasets with equal class distribution
Specificity	Of all actual negatives, how many were correctly identified?	Minimising false alarms
MCC	Overall quality of binary classifier, range -1 to +1	Imbalanced datasets — more informative than accuracy

Precision vs Recall Trade-off

Precision and recall are inversely related in most classifiers. Increasing the decision threshold raises precision (fewer false positives) but lowers recall (more false negatives). The optimal balance depends on your application:

Medical diagnosis: maximise recall — missing a disease is far worse than a false alarm.
Spam detection: maximise precision — blocking legitimate email is more disruptive than missing spam.
Search ranking: precision@k matters more than overall recall for top results.
Fraud detection: recall is critical — missing fraud is expensive; false alerts are manageable.

Frequently Asked Questions

What is the difference between precision and recall?

Precision answers: of all predictions labeled positive, how many were correct? Recall answers: of all actual positives in the dataset, how many did the model identify? A model can have high precision with low recall (conservative) or high recall with low precision (aggressive).

When should I use F1 score instead of accuracy?

Use F1 when your dataset is imbalanced. If 95% of samples are class 0, a model predicting class 0 always achieves 95% accuracy but is completely useless. F1 balances precision and recall and is not inflated by a dominant class.

What is MCC (Matthews Correlation Coefficient)?

MCC is a correlation coefficient between actual and predicted binary classifications. It ranges from -1 (inverse prediction) to +1 (perfect prediction), with 0 representing random prediction. It is considered the most informative single metric for binary classification on imbalanced data.

What does a False Positive mean?

A False Positive (Type I error) occurs when the model predicts Positive but the true label is Negative. In spam detection: a legitimate email flagged as spam. In medical testing: a healthy patient testing positive for a disease.

Can this calculator handle multi-class classification?

This tool is designed for binary classification (one positive class vs one negative class). For multi-class problems, compute per-class TP/FP/FN/TN using a one-vs-rest approach and then macro/micro average the metrics.

Related Tools

🎯

Model Accuracy Calculator

Calculate machine learning model accuracy instantly. Compare actual vs predicted labels, evaluate AI performance, upload CSV data, and get instant results online for free.

Try it now→

🤖

AI Token Cost Calculator

Estimate AI API token costs for OpenAI, Claude, Gemini, and custom models. Calculate prompt and completion token expenses, compare models, and forecast monthly and yearly costs.

Try it now→

📏

AI Prompt Length Calculator

Calculate AI prompt length instantly. Count tokens, words, characters, sentences, and estimate context window usage for ChatGPT, Claude, Gemini, and other AI models.

Try it now→

📊

Time Complexity Calculator

Estimate algorithm time complexity using Big-O notation. Analyze loop patterns, recursion, and algorithm presets with interactive growth visualizations and educational explanations.

Try it now→

⏱️

Latency Calculator

Estimate network latency, propagation delay, transmission delay, round-trip time (RTT), and gaming ping. Free online latency calculator for networking, gaming, cloud, and DevOps.

Try it now→

⏱️

Data Transfer Calculator

Calculate how long it will take to transfer data based on file size and network speed. Supports downloads, uploads, backups, cloud migrations, and enterprise data transfers with real-time results.

Try it now→