Ons werk controleren
Komen de waarschijnlijkheden uit?
Wanneer het model zegt dat een team 70% kans heeft, zou dat team ongeveer zeven van de tien keer moeten winnen. Deze pagina controleert of dat zo is. Elke WK 2026-wedstrijd wordt beoordeeld zodra deze is gespeeld, en de onderstaande cijfers stellen een vraag: zijn de waarschijnlijkheden eerlijk, niet alleen overtuigend? (De technische term hiervoor is kalibratie.)
Track record
Proven on past tournaments
The short version: when the model says 70%, it happens about 70%. Across these 987 matches its stated chances landed within ~5.6 points of reality, and on average it rated the actual result about 35% more likely than a blind 1-in-3 guess would.
The 2026 tracker below stays empty until the first match kicks off. So to show the model has been tested, not just described, we ran it against tournaments whose results you already know. For each one, the model was rebuilt exactly as it stood the day before kickoff, then graded on every match — it never sees the result it is being marked on. That is what “graded out of sample” means: no peeking, no hindsight.
Each tournament is scored by the production model reconstructed as it stood the day before the tournament's first match: Dixon-Coles and Hierarchical Poisson refit on matches strictly beforehand, Elo rolled forward to each match, and the tournament-tier calibration layer refit on the 24 months of matches before the cutoff. No data from the tournament, or any later match, touches any layer of the fit.
Graded across 987 matches at 24 major tournaments (2014–2024)
- 0.572
- 1.000
- 5.6pp
How close the forecasts landed to reality. Lower is better; blind 1-in-3 guessing scores ≈ 0.667.
Like Brier, but overconfidence is punished harder. Lower is better; blind guessing scores ≈ 1.099.
Does “70%” really mean 70%? The average gap between the two. Lower is better.
Tournament by tournament
One row per tournament: the model rebuilt as it stood the day before it began, then graded on every match through the final (Brier — lower is better, blind 1-in-3 guessing is 0.667). A few thin, early editions sit above that line; the honest measure is all of them pooled, in the box above.
| Tournament | Host | Matches | Brier |
|---|---|---|---|
| Copa América 2024 | United States | 32 | 0.522 |
| Euro 2024 | Germany | 51 | 0.613 |
| AFCON 2024 | Ivory Coast | 52 | 0.651 |
| Asian Cup 2024 | Qatar | 51 | 0.515 |
| Gold Cup 2023 | United States | 31 | 0.566 |
| World Cup 2022 | Qatar | 64 | 0.611 |
| AFCON 2022 | Cameroon | 52 | 0.686 |
| Gold Cup 2021 | United States | 31 | 0.341 |
| Copa América 2021 | Brazil | 28 | 0.481 |
| Euro 2021 | England | 51 | 0.554 |
| AFCON 2019 | Egypt | 52 | 0.546 |
| Gold Cup 2019 | United States | 31 | 0.405 |
| Copa América 2019 | Brazil | 26 | 0.542 |
| Asian Cup 2019 | United Arab Emirates | 51 | 0.496 |
| World Cup 2018 | Russia | 64 | 0.569 |
| Gold Cup 2017 | United States | 25 | 0.456 |
| AFCON 2017 | Gabon | 32 | 0.642 |
| Euro 2016 | France | 51 | 0.668 |
| Copa América 2016 | United States | 32 | 0.502 |
| Gold Cup 2015 | United States | 26 | 0.755 |
| Copa América 2015 | Chile | 26 | 0.686 |
| AFCON 2015 | Equatorial Guinea | 32 | 0.795 |
| Asian Cup 2015 | Australia | 32 | 0.434 |
| World Cup 2014 | Brazil | 64 | 0.565 |
Reliability diagram
Read it like this: each dot is a group of similar forecasts. left-to-right is what the model predicted, bottom-to-top is how often it actually happened. When the model says 70% and that happens about 70% of the time, the dot sits on the dashed line: perfect calibration. The closer the dots hug the line, the more honest the probabilities; bigger dots mean more matches in that group.
Brier by favourite confidence
Matches grouped by how confident the model's favourite was (its biggest of the home / draw / away probabilities) — so you can see whether it is as reliable on toss-ups as on heavy favourites.
| Favourite confidence | Matches | Brier |
|---|---|---|
| P_fav < 40% | 81 | 0.649 |
| P_fav 40-60% | 476 | 0.633 |
| P_fav 60-80% | 318 | 0.512 |
| P_fav >= 80% | 112 | 0.428 |
- Out-of-sample: the calibration layer is refit per tournament on pre-tournament data, so these numbers do not reuse the live shipped calibrator (which has seen these results).
- The uniform 1/3 forecast scores a Brier of 0.667; lower is better. Major-tournament football is high-variance, so a strong model still sits well above a league-season Brier.
- Calibrated and uncalibrated metrics are reported on the same fixtures so the calibration layer's effect is visible.
Built 2026-05-30 · model 1.0.0 · calibration layer refit on the 24 months before each tournament.
WK 2026: live tracker
Across 96 graded forecasts so far, the model's overall Brier score is 0.497 (lower is better; blind 1-in-3 guessing scores ≈ 0.667). The reliability diagram below plots what the model predicted against how often it actually came true. The closer to the diagonal, the more honest the probabilities.
Overall, across 96 scored matches
- 0.497
- 0.837
- 0.167
How close the forecasts landed to reality. Lower is better; blind 1-in-3 guessing scores ≈ 0.667.
Like Brier, but overconfidence is punished harder. Lower is better; blind guessing scores ≈ 1.099.
Does “70%” really mean 70%? The average gap between the two. Lower is better.
Rolling Brier, 10-match window
The model's accuracy over its most recent 10 matches, re-figured after each game. Lower is better; the dashed line is what blind 1-in-3 guessing would score, so anything below it is real skill.
Per-matchday breakdown
| Date | Matches | Brier | Log loss |
|---|---|---|---|
| 2026-06-11 | 2 | 0.404 | 0.723 |
| 2026-06-12 | 2 | 0.817 | 1.280 |
| 2026-06-13 | 4 | 0.771 | 1.178 |
| 2026-06-14 | 4 | 0.595 | 1.008 |
| 2026-06-15 | 4 | 1.148 | 1.632 |
| 2026-06-16 | 4 | 0.197 | 0.438 |
| 2026-06-17 | 4 | 0.640 | 1.005 |
| 2026-06-18 | 4 | 0.426 | 0.739 |
| 2026-06-19 | 4 | 0.463 | 0.787 |
| 2026-06-20 | 4 | 0.531 | 0.854 |
| 2026-06-21 | 4 | 0.603 | 0.928 |
| 2026-06-22 | 4 | 0.266 | 0.529 |
| 2026-06-23 | 4 | 0.433 | 0.706 |
| 2026-06-24 | 6 | 0.410 | 0.750 |
| 2026-06-25 | 6 | 0.506 | 0.868 |
| 2026-06-26 | 6 | 0.388 | 0.704 |
| 2026-06-27 | 6 | 0.434 | 0.763 |
| 2026-06-29 | 2 | 0.612 | 0.996 |
| 2026-06-30 | 3 | 0.500 | 0.866 |
| 2026-07-01 | 3 | 0.478 | 0.830 |
| 2026-07-02 | 3 | 0.327 | 0.622 |
| 2026-07-03 | 3 | 0.460 | 0.796 |
| 2026-07-04 | 1 | 0.225 | 0.470 |
| 2026-07-06 | 2 | 0.443 | 0.784 |
| 2026-07-07 | 2 | 0.541 | 0.909 |
| 2026-07-09 | 1 | 0.573 | 0.960 |
| 2026-07-10 | 1 | 0.280 | 0.564 |
| 2026-07-11 | 2 | 0.250 | 0.517 |
| 2026-07-15 | 1 | 0.537 | 0.911 |
Updated 2026-07-16.
Reliability diagram
Read it like this: each dot is a group of similar forecasts. left-to-right is what the model predicted, bottom-to-top is how often it actually happened. When the model says 70% and that happens about 70% of the time, the dot sits on the dashed line: perfect calibration. The closer the dots hug the line, the more honest the probabilities; bigger dots mean more matches in that group.
Brier by competition
| Segment | Matches | Brier | Δ vs overall |
|---|---|---|---|
| World Cup 2026 | 96 | 0.497 | +0.000 |
Brier by tournament stage
| Segment | Matches | Brier | Δ vs overall |
|---|---|---|---|
| Group stage | 72 | 0.516 | +0.019 |
| Round of 32 | 15 | 0.449 | -0.048 |
| Round of 16 | 4 | 0.492 | -0.005 |
| Quarter-final | 4 | 0.338 | -0.159 |
| Semi-final | 1 | 0.537 | +0.039 |
| Third-place play-off | — | — | — |
| Final | — | — | — |
Brier by favourite confidence
| Segment | Matches | Brier | Δ vs overall |
|---|---|---|---|
| P_fav < 40% | 11 | 0.669 | +0.172 |
| P_fav 40-60% | 47 | 0.540 | +0.043 |
| P_fav 60-80% | 32 | 0.373 | -0.125 |
| P_fav >= 80% | 6 | 0.513 | +0.016 |
Wat de drie getallen betekenen
Denk aan een weerman. Iedereen kan zeggen: "70% kans op regen." De goeden hebben daadwerkelijk ongeveer 70% van de tijd gelijk als ze dat zeggen. Deze drie getallen controleren het model op dezelfde manier.
- Brier score: lagen de waarschijnlijkheden dicht bij de werkelijkheid? Voor elke wedstrijd meten we hoe ver de voorspelling van de werkelijkheid lag, en dan nemen we het gemiddelde. Een perfecte kristallen bol scoort 0; blind raden (1-op-3 per keer) scoort ongeveer 0,667. Lager is beter.
- Log loss: hetzelfde idee, maar overdreven vertrouwen wordt hard bestraft. Noem iets bijna zeker en krijg het vervolgens fout, en dit getal springt omhoog. Het is de maatstaf die het model bescheiden houdt. Blind raden scoort ongeveer 1,099. Lager is beter.
- ECE: betekent "70%" echt 70%? We verzamelen alle voorspellingen van "ongeveer 70%" en controleren hoe vaak die dingen daadwerkelijk gebeurden. Het gemiddelde verschil, over elk betrouwbaarheidsniveau, is de ECE. Een paar procentpunten betekent dat de genoemde kansen op hun woord genomen kunnen worden. Lager is beter.
De eerste twee belonen juist en gedurfd zijn; de laatste is de eerlijkheidscontrole. Een model kan er indrukwekkend uitzien en toch zijn vertrouwen overschatten. Alle drie tegelijk meten is wat dat ontdekt.
Wil je het mechanisme erachter, de componentmodellen en de held-out test achter deze getallen? Het staat allemaal op de methodologie-pagina.