Final score 2-3. Below is what the model published before kick-off, and how each market was graded.
20 September 2026 at 19:00 UTC
| Market | Model says | Probability |
|---|---|---|
| Match result Miss | Valencia win | 50% |
| Both teams to score Hit | Both score | 51% |
| Over / under Miss | Under 3.5 goals | 74% |
| Double chance Miss | Valencia or draw | 76% |
| Clean sheet Miss | Valencia clean sheet | 37% |
| Correct score Miss | 1-1 | 13% |
| First goal | Valencia score first | 56% |
| Half time / full time | Valencia / Valencia | 31% |
| Total corners Hit | Over 8.5 corners | 69% |
| Total cards Hit | Under 5.5 cards | 74% |
Each row is a calibrated probability, not a tip. The model is fitted on historical results, re-run when the lineup lands, and every market here is settled and graded once the match is over — the verdict stays on the page whether it went our way or not. Market-level records live on the predictions board.
Every market on every match, the edge against the market price and the AI panel live in the app - and the Accuracy Ledger is free in it.
Get it on Google Play