The model on 25 October: 78 out of 157
Of the 157 matches our model predicted before kick-off on Sunday 25 October 2026, it called the result of 78 (50%). It named the exact scoreline 18 times. Across all 4,942 matches it has predicted since 19 July, the rate is 48%.
What stood out
At 50% the day was in line with the model's running rate. The result it least expected was Sporting CP 1-2 Academico Viseu: it had given a win for Academico Viseu 15%. Its best competition of the day was Primera División (Peru) (5 of 5), its weakest Liga Pro (Ecuador) (0 of 3).
By competition
- Major League Soccer: 1 of 7
- Eliteserien: 4 of 6
- Ligue 1: 2 of 6
- Eredivisie: 2 of 5
- Persian Gulf Pro League: 2 of 5
- Premier League (England): 0 of 5
- Primera División (Peru): 5 of 5
- Serie A (Italy): 4 of 5
- 43 other competitions: 58 of 113
The most confident misses
The predictions it was surest about and got wrong:
- Sporting CP 1-2 Academico Viseu: the model had Sporting CP at 65%.
- Toulouse 0-0 Estac Troyes: the model had Toulouse at 64%.
- Sturm Graz 2-2 Ried: the model had Sturm Graz at 60%.
Exact scorelines
- Borac Banja Luka 2-0 Sloga Doboj: the exact score it named, with Borac Banja Luka at 80%.
- Inter 2-1 Fiorentina: the exact score it named, with Inter at 67%.
- Zenit 2-0 Dinamo Makhachkala: the exact score it named, with Zenit at 67%.
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.