Final score 5-4. Below is what the model published before kick-off, and how each market was graded.
16 October 2026 at 11:00 UTC
| Market | Model says | Probability |
|---|---|---|
| Match result Hit | Univer Comrat win | 78% |
| Both teams to score Hit | Both score | 62% |
| Over / under Hit | Over 1.5 goals | 92% |
| Double chance Hit | Univer Comrat or draw | 91% |
| Clean sheet Miss | Univer Comrat clean sheet | 35% |
| Correct score Miss | 3-1 | 8% |
| First goal | Univer Comrat score first | 73% |
| Half time / full time | Univer Comrat / Univer Comrat | 55% |
| Total corners | Over 8.5 corners | 69% |
| Total cards | 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