Champions League · 2026-27
Win, draw and loss probabilities for every tournament match, from a Poisson-goals model built on a European rating ladder. Each card shows what is driving the call, in probability points.
How 1372 tournament matches actually finished, in regular time. This is the competition itself, not our model: it is the ground the probabilities on this page are measured against.
Across the decade 46.5% of matches ended in a home win, 33.6% away and 19.9% drawn. The draw is the rarest of the three, and the hardest of the three to call.
Bars run from zero to 4.0 goals, and the dashed line is the decade average of 3.12. The last two seasons are the 36-club league phase, 189 matches a season instead of 125, and the two highest goal counts of the decade.
A European rating ladder walked over Champions League and Europa League matches, each club's recent scoring and conceding rates in Europe, its domestic league standing, and home advantage. Those five things are exactly the factors shown on each card.
Every match of the tournament proper, from the opening league phase round through to the final in May, each one published days ahead of kick-off.
As a long-run frequency. If the model says 62%, then across the matches where it says 62%, the home side should win about 62 of every 100. A 62% call that loses is not a wrong call, it is one of the 38.
The model works by first estimating how often each side scores, then turning those scoring rates into the result probabilities above. The rates are shown so you can see which side is expected to create more. Read them as that comparison, not as a score prediction: the numbers sit lower than real goal counts.
Cards are published as soon as a tournament fixture is inside the next week and are re-scored daily as new results move the ratings. At kick-off the number is frozen, and the match page then shows it next to what actually happened.
The Champions League match predictions dataset is free to reuse, including commercially, under CC BY 4.0. Attribution with a link is the only requirement. Copy-paste credit:
Data: <a href="https://www.predixsport.com/champions_league_predictions">Champions League match predictions by Predixsport</a> (CC BY 4.0)Predixsport publishes probabilistic forecasts for NBA, football, and tennis matches using calibrated machine-learning models.
The data is intended for fans, analysts, journalists, and researchers interested in sports modeling. See our methodology and model transparency pages for train/test splits, calibration curves, error metrics, and known model limitations.
No forecast is a guarantee. Sports events are inherently uncertain, and even well-calibrated probabilities will be wrong on individual matches. Our published calibration data shows the actual long-run error rates. Bookmaker odds reflect equally sophisticated models, and differences are typically small and noisy.
Liability and personal-use note. Predixsport does not provide financial, investment, or betting advice. Any decision to act on these forecasts (including but not limited to placing bets or wagers of any kind) is entirely your own and made at your own risk. Predixsport.com, its owners, employees, contributors, and affiliates accept no liability for any losses or damages arising from the use of, or reliance on, the information published on this website.
If gambling is causing harm to you or someone close, support is available: Gamblers Anonymous, National Council on Problem Gambling.