F-beta Score Calculator
Calculate the F-beta score with a configurable weight between precision and recall.
About F-beta Score Calculator
The F-beta score generalizes F1 into a weighted harmonic mean of precision and recall: F_β = (1 + β²) × (P × R) / (β² × P + R). Setting β = 1 recovers the standard F1 score (equal weight). Setting β > 1 (commonly β = 2) weighs recall more heavily than precision, useful when missing positives is costlier than false alarms. Setting β < 1 (commonly β = 0.5) weighs precision more heavily, useful when false positives are costlier.
Formula
F_beta = (1 + beta^2) * (precision * recall) / (beta^2 * precision + recall)
- P
- Precision
- R
- Recall
- \beta
- Beta weight parameter
Worked example
With the default values below, F-beta Score Calculator returns F-Beta Score of 0.6316. Change any input above and every figure here is recalculated in your browser.
Inputs used
- Precisionaccepts 0–1
- 0.8
- Recallaccepts 0–1
- 0.6
- Betaaccepts 0.01–10
- 2
Results
- F-Beta Score
- 0.6316
- Beta²
- 4.0000
Step by step
- 1Beta squared: beta²= 4.0000
- 2F-beta: (1 + beta²) × (P × R) / (beta² × P + R)= 0.6316
Assumptions and limits
- The result is derived only from the 3 inputs listed above. Anything not among them is not part of the calculation.
- In particular, this calculator does not take inflation, tax, fees or charges or compounding frequency into account.
- Figures are rounded for display to 4 decimal places, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.
How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.
Frequently Asked Questions
What's the difference between F0.5, F1, and F2?
F0.5 weighs precision twice as much as recall, F1 weighs them equally, and F2 weighs recall twice as much as precision — choose based on which error type (false positive vs. false negative) is more costly for your use case.
Why would I use F2 instead of F1?
F2 is common in domains like medical screening or fraud detection where missing a true positive (a false negative) is much worse than a false alarm, so recall is weighted more heavily in the combined score.
Can I compute F-beta directly from TP/FP/FN instead of precision/recall?
Yes — first compute precision = TP/(TP+FP) and recall = TP/(TP+FN) using the Precision and Recall Calculators, then enter those values here.