The model on 14 October: 15 out of 38
Of the 38 matches our model predicted before kick-off on Wednesday 14 October 2026, it called the result of 15 (39%). It named the exact scoreline once. Across all 3,746 matches it has predicted since 19 July, the rate is 48%.
By competition
- UEFA Champions League: 4 of 9
- Major League Soccer: 3 of 6
- 3. Liga: 0 of 5
- Championship: 4 of 4
- 1. Lig: 1 of 3
- AFC Champions League Elite: 2 of 2
- CONMEBOL Sudamericana: 1 of 2
- Ligue 1: 0 of 2
- 5 other competitions: 0 of 5
The most confident misses
The predictions it was surest about and got wrong:
- FC Viktoria Köln 2-2 SG Sonnenhof Grossaspach: the model had FC Viktoria Köln at 66%.
- Junior 1-1 Deportivo Pereira: the model had Junior at 64%.
- Manchester City 2-4 Paris Saint Germain: the model had Manchester City at 57%.
Exact scorelines
- DC United 2-1 New York Red Bulls: the exact score it named, with DC United at 40%.
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.