Part of the AI & Machine Learning suite · 24 calculators

Preference Win Rate Calculator

From a set of pairwise preference judgements between two models or responses — wins, losses and ties — the win rate, its confidence interval, the Elo-style rating gap it implies, and how many more comparisons you need to tighten it.

Preference data is the raw material of reward models and of every leaderboard that ranks by head-to-head votes.

Results update as you type
Results
Win rate for A
60.91%
Comparisons
95% interval, low
95% interval, high
Implied Elo gap
Elo gap across the interval
Is A better than a coin flip?
Comparisons for the margin you want
Current margin (± points)
Reviewed September 2026. Model arithmetic is the same everywhere: the same formulas in every market, in your own currency. Australia's AI Ethics Principles are voluntary; cost and sizing arithmetic carries no regulatory requirement.
No account required · Google Analytics off unless allowedCalculator arithmetic runs in your browserResults update as you type
All calculations run 100% in your browser. The calculator code does not submit your figures to GlobalCalc to obtain a result.
About preference win rate

How the preference win rate calculator works

Preference data is the raw material of reward models and of every leaderboard that ranks by head-to-head votes. A win rate of 60% is an Elo gap of about 70 points; 75% is about 190. But a win rate from thirty comparisons is a guess — the Wilson interval says how wide — and the comparisons needed for a given margin grow with the square of the precision you want.

Ties count as half a win, which is the convention in rating systems and in most preference datasets.

Formula: p = (wins + ½ ties) / n; Elo gap = 400 log₁₀(p / (1 − p)); n for margin m ≈ z² p(1−p) / m²

Worked examples

InputsWin rate for ANote
62 to 38 with 10 ties60.91%61% — clearly better
A handful of judgements70%70%, but the interval touches 50
A large evaluation52.5%52.5%, and significant

Frequently asked questions

What is a preference win rate?

The share of pairwise judgements in which one model's output was preferred over another's, with ties as half. It is the basic statistic of RLHF data and of chatbot arenas.

How does win rate become an Elo gap?

Through the logistic rating model: a rating gap of 400 points means a 10:1 win expectation. Sixty per cent is about 70 points; seventy-five per cent about 190.

Why a Wilson interval?

Because the usual normal approximation misbehaves at small counts and near 0 or 100%. Wilson stays inside the possible range and is right at small n.

How many comparisons do I need?

For a ±3-point margin at 95%, about a thousand. For ±1 point, nearly ten thousand. The cost grows with the square of the precision.

Do annotator disagreements matter?

Very much — a win rate has an irreducible ceiling set by how often humans agree with each other. Measure inter-annotator agreement alongside this.

Where these figures come from

Last checked: September 2026. The relationships here are architectural, not vendor-specific: bytes per parameter follow the numeric format, KV-cache size follows the transformer definition, and token-per-word ratios come from published tokeniser behaviour.