F-beta Score Calculator
Weighted harmonic mean of precision and recall — tune β to favor recall (β>1) or precision (β<1) for your problem.
F2 (β=2) is standard when missing positives is costly (medical screening, fraud recall); F0.5 (β=0.5) when false alarms are costly (spam, recommendation precision). F1 (β=1) weighs them equally.
Formula
About F-beta Score Calculator
F1 weighs precision and recall equally — but most real problems don't. The F-beta score generalizes it with a single knob: β is how many times more important recall is than precision. Use F2 when a missed positive (undiagnosed disease, undetected fraud) hurts more than a false alarm; use F0.5 when false alarms (spam in the inbox, irrelevant recommendations) are the costlier mistake. This calculator computes Fβ for any β and shows F1 alongside so you can see exactly how the weighting shifts the score.
How to use F-beta Score Calculator
- 1Enter your values into F-beta Score Calculator — sensible, domain-typical defaults are pre-filled so you see a real result immediately.
- 2The result recomputes live using the formula shown on the page; there is no button to press.
- 3Adjust any input to compare scenarios, then read the worked example to see the substituted numbers.
Why use F-beta Score Calculator?
- ✓Computes F-beta Score instantly in your browser — no sign-up, no upload, no server round-trip.
- ✓100% free and unlimited, with the exact formula shown: Fβ = (1+β²).
- ✓Runs entirely client-side, so every value you enter stays private on your device.
- ✓Live recompute as you type, with a worked example and authoritative references for trust.
Frequently asked questions
How do I choose β?+
Set β to the ratio of false-negative cost to false-positive cost. If missing a positive is 4× worse than a false alarm, β=2 (β² ≈ 4) roughly encodes that. It's a heuristic, not exact decision theory, but it aligns the metric with your real priorities far better than defaulting to F1.
Why a harmonic mean instead of an average?+
The harmonic mean punishes imbalance: a model with precision 1.0 and recall 0.0 has an arithmetic mean of 0.5 but an F-score of 0. This forces both quantities to be reasonable, preventing the metric from rewarding a model that's excellent at one and useless at the other.
What are F2 and F0.5 exactly?+
F2 (β=2) weights recall four times as heavily as precision in the denominator — the screening/fraud default. F0.5 (β=0.5) weights precision four times as heavily — the spam/recommendation default. Both are just Fβ with specific β values, computed identically by this tool.
Can Fβ exceed 1 or go negative?+
No — like precision and recall, it's bounded in [0, 1], where 1 means perfect on both. (That distinguishes it from MCC, which spans −1 to +1.) If you're seeing values outside this range, your precision or recall inputs are outside [0, 1].
Related tools
- Macro / Micro / Weighted F1 Calculator
- PPV / NPV & Prevalence Calculator
- Balanced Accuracy & Youden's J Calculator
- Classification Metrics — Confusion Matrix & Metrics Calculator
- Spam Filter — Confusion Matrix & Metrics Calculator
- Medical Diagnostic Test — Confusion Matrix & Metrics Calculator
- Vector Distance Calculator (Euclidean, Manhattan, Chebyshev, Minkowski)
- Levenshtein Edit Distance Calculator
Related ML & AI tools
ROC-AUC Calculator (from TPR/FPR points)
Trapezoidal area under the ROC curve from your (FPR, TPR) operating points — the threshold-independent ranking score.
● LiveClassification Threshold Cost Calculator
Find the probability cutoff that minimizes expected cost given your false-positive and false-negative penalties.
● LiveSilhouette Score Calculator
Cluster cohesion vs separation for one point — the building block of the silhouette metric for choosing K.
● Live