The model on 24 October: 107 out of 239
Of the 239 matches our model predicted before kick-off on Saturday 24 October 2026, it called the result of 107 (45%). It named the exact scoreline 24 times. Across all 4,776 matches it has predicted since 19 July, the rate is 48%.
What stood out
At 45% the day ran 3 points below the model's running rate of 48%. The result it least expected was Bodo/Glimt 0-1 Valerenga: it had given a win for Valerenga 11%. Its best competition of the day was Super League (Switzerland) (3 of 3), its weakest A-League (Australia) (0 of 3).
By competition
- League One: 5 of 12
- Championship (England): 5 of 11
- League Two: 5 of 11
- Super League (China): 3 of 8
- Serie B (Italy): 3 of 7
- 3. Liga: 3 of 6
- Bundesliga (Germany): 3 of 6
- K League 1: 2 of 6
- 56 other competitions: 78 of 172
The most confident misses
The predictions it was surest about and got wrong:
- Shakhtar Donetsk 0-0 Zorya Luhansk: the model had Shakhtar Donetsk at 75%.
- Djurgardens IF 2-2 Orgryte IS: the model had Djurgardens IF at 74%.
- Bodo/Glimt 0-1 Valerenga: the model had Bodo/Glimt at 73%.
Exact scorelines
- Arsenal 2-0 Everton: the exact score it named, with Arsenal at 63%.
- CF Montreal 0-2 Nashville SC: the exact score it named, with Nashville SC at 60%.
- Reading 2-1 Barnsley: the exact score it named, with Reading at 59%.
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.