Cricket win probability

One number: the chance a side wins from where the match stands right now. Here is what goes into it, how to read it, and what it has actually scored.

The definition

Win probability is not a rating of how well a team has played. It is a forecast from the current position, and it holds no memory of how that position was reached. A side that collapsed to 40 for 5 and recovered to 130 for 5 is read exactly the same as a side that reached 130 for 5 serenely, because from here the two are the same problem.

What goes into it

Those feed a gradient-boosted model trained on roughly a decade of ball-by-ball T20 records, which is then updated over by over: each over is treated as evidence for or against the reading the model already held, so a single expensive over shifts the number without overturning it.

How to read it

A high number is not a promise

85% means that in a hundred matches from positions like this one, about fifteen are lost. T20 is a format where fifteen in a hundred happens often enough to watch for.

Early readings are worth less

At over 6 the model scores about 79%; by over 15 it is about 82%. It knows less early because there is less to know, and it says so rather than presenting every reading with equal confidence.

Movement is information

A number that barely moves through a 20-run over would be wrong more often, not less. What the model avoids is reacting to noise — each over is weighed against what was expected at that stage.

Is it any good? The two tests

Test one: direction

81.5% of the time the favoured side went on to win, across 19,340 predictions on 2,546 matches from 2025-26 that were held out of training entirely.

Reading taken atAccuracy
After Over 679.2%5,036
After Over 1082.1%4,926
After Over 1282.6%4,820
After Over 1582.2%4,558

Test two: calibration

This is the harder test and the one that matters. Group every prediction by what the model said, then check what actually happened in each group. A model that only ever backs the obvious favourite can post a strong hit-rate; it cannot post a straight calibration line.

Model saidPredictionsActually won
0-10%4,5293.8%1.2
10-20%1,56415.3%0.3
20-30%1,18825.4%0.4
30-40%1,07434.5%0.5
40-50%1,17543.9%1.1
50-60%1,12250.4%4.6
60-70%1,35062.1%2.9
70-80%1,56872.5%2.5
80-90%1,70881.1%3.9
90-100%4,06296.1%1.1

Full method and the reproduction command are on the accuracy page.

What it is not

It is not a tip, a price, or advice. It carries no ball-tracking data — speed, swing and spin measurements are not available to us at this scale, and the model works from delivery outcomes only. And it says little before the first ball, because from nothing there is little to forecast.

See it live · How it works · FAQ