Part of the AI & Machine Learning suite · 36 calculators

Bradley–Terry Calculator

The Bradley–Terry strength ratio and win probability between two models or responses from how often each was preferred — with an Elo-style rating gap and a confidence interval on the win rate.

In the Bradley–Terry model each competitor has a strength, and the probability A beats B is s_A ÷ (s_A + s_B).

Results update as you type
Results
Probability A beats B
59.1 %
Strength ratio A : B
Rating gap (Elo-style points)
95% interval on A’s win rate
Reads as
Reviewed September 2026. Model arithmetic is the same everywhere: the same formulas in every market, in your own currency. The NIST framework is voluntary guidance; it does not prescribe cost or sizing methods.
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 bradley–terry

How the bradley–terry calculator works

In the Bradley–Terry model each competitor has a strength, and the probability A beats B is s_A ÷ (s_A + s_B). From head-to-head counts the maximum-likelihood ratio is simply wins_A ÷ wins_B, so a 60–40 preference is a strength ratio of 1.5. Chatbot arenas convert it to an Elo-like scale: 400 × log₁₀ of the ratio — 60% is about 70 points. The Wilson interval shows how sure the counts make you.

Formula: P(A beats B) = s_A ÷ (s_A + s_B); s_A ÷ s_B = wins_A ÷ wins_B; rating gap = 400 log₁₀(s_A ÷ s_B)

Worked examples

InputsProbability A beats BNote
120 to 80 with 20 ties59.1 %59.1%, ratio 1.44, +64 points
A narrow lead from few comparisons55 %55% but not significant
A dominant model90 %90% — +382 points

Frequently asked questions

What is the Bradley–Terry model used for?

Any ranking from pairwize comparisons: chess and sports ratings (Elo is a special case), chatbot leaderboards built from human preferences, and reward models in RLHF, which are trained to reproduce these preference probabilities.

How many comparisons do I need?

The interval row tells you: 200 comparisons at 60–40 give roughly 53–67%, enough to be confident A is better; 20 comparisons at the same rate are not. Aim for a few hundred per pair for a stable rating.

How do ties count?

Half a win to each side, the usual convention. Some arenas drop ties instead; the effect on the ratio is small unless ties dominate.

How does this extend to many models?

Fit strengths for all models jointly by maximum likelihood from every pair’s counts (the arena leaderboards do this with a logistic regression). The two-model case here is the building block.

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.