The model on 21 October: 14 out of 23
Of the 23 matches our model predicted before kick-off on Wednesday 21 October 2026, it called the result of 14 (61%). It named the exact scoreline once. Across all 4,396 matches it has predicted since 19 July, the rate is 48%.
What stood out
At 61% the day ran 13 points above the model's running rate of 48%. The result it least expected was Sporting CP 2-3 Lask Linz: it had given a win for Lask Linz 8%. Its best competition of the day was UEFA Champions League (6 of 9), its weakest Premier League (Egypt) (1 of 3).
By competition
- UEFA Champions League: 6 of 9
- Liga MX: 2 of 4
- Premier League: 1 of 3
- CONMEBOL Sudamericana: 1 of 2
- Finnish Premier League: 0 of 1
- La Liga: 1 of 1
- League One: 1 of 1
- Major League Soccer: 1 of 1
- 1 other competitions: 1 of 1
The most confident misses
The predictions it was surest about and got wrong:
- Sporting CP 2-3 Lask Linz: the model had Sporting CP at 80%.
- Tigres UANL 0-2 Leon: the model had Tigres UANL at 54%.
- Al Ahly 3-3 Olympic El Qanah: the model had Al Ahly at 53%.
The exact scoreline
FC Cincinnati 2-1 DC United: the exact score it named, with FC Cincinnati at 51%.
How this is counted
A result counts as called when the outcome the model rated most likely (home win, draw or away win) is the one that happened. Every prediction here was published and logged before kick-off, and the log is public: the track record breaks it down by confidence, by competition and by club. How the probabilities are produced, including where the model is known to be wrong, is in the methodology.
Every evening on Telegram
This summary is posted each evening on our Telegram channel, t.me/fulltimestats_com, with a link back to the full recap.