The model on 27 September: 17 out of 33
Of the 33 matches our model predicted before kick-off on Sunday 27 September 2026, it called the result of 17 (52%). It named the exact scoreline 5 times. Across all 2,909 matches it has predicted since 19 July, the rate is 47%.
By competition
- Major League Soccer: 5 of 10
- UEFA Nations League: 5 of 8
- Segunda División: 4 of 5
- Botola Pro: 1 of 3
- Liga MX: 1 of 3
- Primera A: 1 of 3
- K League 1: 0 of 1
The most confident misses
The predictions it was surest about and got wrong:
- Vancouver Whitecaps 3-3 DC United: the model had Vancouver Whitecaps at 57%.
- Houston Dynamo 0-2 Sporting Kansas City: the model had Houston Dynamo at 53%.
- Pumas UNAM 2-3 Atletico San Luis: the model had Pumas UNAM at 50%.
Exact scorelines
- Nashville SC 2-0 Toronto FC: the exact score it named, with Nashville SC at 54%.
- Serbia 1-2 Netherlands: the exact score it named, with Netherlands at 49%.
- Tigres UANL 1-0 Puebla: the exact score it named, with Tigres UANL at 47%.
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.