Prediction review
Saturday, 5 September 2026
On 2026-09-05 we had published a prediction for 96 fixtures before kick-off. We called 44 of them correctly, 46%.
Our strongest call
The call we backed hardest was Manchester City to beat Coventry City in Premier League, at 84.6%, and it held. It finished 1–0.
Where we were most wrong
VfL Wolfsburg against Energie Cottbus finished 4–4. We had published VfL Wolfsburg to beat Energie Cottbus at 77.7%, the largest confidence we placed on an outcome that did not happen. It stays on the record: a site that reports only its hits is not reporting a record, it is reporting a selection.
When we were confident
21 of the day's calls were at 60% or above. 9 of them landed. Over a single day that number means very little — it is the same figure across a month that says whether our stated confidence is honest.
The ones we called close
18 fixtures were split closely enough that no outcome reached 40%. 4 of them ended level. We publish these without pretending to a view: a fixture the model divides three ways is one it has little to tell you about, and saying so is more useful than manufacturing a lean.
Coverage
The day's predictions spanned 21 competitions: Championship (11), League One (11), League Two (11).
Only predictions published before the match day are counted. Results come from public fixture feeds. How the model is measured →