Analysis — Champions League
Short pieces built on the same computations as the tables. The figures in them are not copied out: they follow the model.
Lens 1-9 Como: a one-in-500,000 result, as unlikely as 19 heads in a row
Before kick-off, our model saw a tight game, with Como slightly ahead and 1-1 as the most likely score. The 1-9 that followed had roughly a one-in-500,000 chance of happening. What that number means, and why lopsided scores always catch models out.
PSG v Barça: our two models don’t pick the same favourite
Six points each, four away goals each on the last matchday, and two opposite readings. Dixon-Coles sees a slight edge for Barça; our player model makes PSG favourites by ten points. What each model looks at, and why they don’t see the same game.
Is PSG the Champions League favourite? Our two models rank it 1st and 10th
Our two models each replayed the 2026-2027 Champions League 50,000 times from the same 18 matches already played, and their rankings correlate at 0.944. On PSG, one gives a 24.5% title chance, the other 2.2%. The whole gap comes down to one question of method: should a squad be judged by its league's average?
Who will win the Champions League in 2026-27?
Arsenal lift the trophy in 25% of simulations, ahead of Manchester City and Bayern. Real Madrid fall to 4%, PSG to 2.2%. Here is the full simulation of the 144-match league phase and the knockout bracket.
Whoever created more clear chances won all six matches. That proves almost nothing.
Six Champions League fixtures last night, and a perfect record on one statistic — while possession says nothing at all. What the match data shows, and what it cannot show.
The probabilitiesfor every matchIn your pocket
These pages show what the model computes. The app compares it with the operators’ odds and flags every value gap. Seven-day trial, no commitment.
18+ · Gamble responsibly · BeGambleAware.org · National Gambling Helpline 0808 8020 133