Football ratings

Monday 14 September 2026 · times UK

The model's strongest calls

78%Inter — home winInter v Udinese · 19:45 · market 77% · this strong, 82% land (2,727 cases)
76%Como — home winComo v Parma · 17:30 · market 79% · this strong, 82% land (2,727 cases)
68%AS Roma — away winTorino v AS Roma · 17:30 · market 62% · this strong, 71% land (1,529 cases)
66%Fenerbahçe — away winGaziantep FK v Fenerbahçe · 18:00 · market 61% · this strong, 71% land (1,529 cases)
£10 on all 4 as one multiple returns about £36 if every one lands. The model puts that at 27%, the market at 23%, and the price needs 28% just to break even.Bookmaker margin compounds with every leg, which is why the break-even sits above the market's own view. A same-match bet builder pays less than this — the bookmaker prices in that the legs move together. Our chance is a straight multiplication and is if anything a little low: where two legs of one match both cleared, they landed together 55.5% of the time against a multiplied 53.4%.

Goals — supporting, not headline

These are calibrated — a 65% call lands about 65% of the time. But the model separates high- from low-scoring matches far less sharply than it separates winners, so there is less information behind a goals number than a result one.

65%Gaziantep FK v Fenerbahçe — over 2.5 goals18:00 · market 55% · this strong, 70% land (1,528 cases)
65%Inter v Udinese — over 2.5 goals19:45 · market 64% · this strong, 66% land (4,584 cases)
57%Moreirense v Maritimo — under 2.5 goals20:15 · market 59% · this strong, 58% land (10,295 cases)

Every fixture

Premier League
Leeds v Newcastle20:00
HomeDrawAway
Model462727
Market422731
Over 2.5Under 2.5
Model5743
Market5347
Under 4.5 goals: 84%  ·  happens 86% of the time anyway
La Liga
Villarreal v Real Betis20:00
HomeDrawAway
Model472627
Market502526
Over 2.5Under 2.5
Model5446
Market6139
Under 4.5 goals: 83%  ·  happens 86% of the time anyway
Serie A
Como v Parma17:30
HomeDrawAway
Model76177
Market79147
Over 2.5Under 2.5
Model5842
Market5842
Under 4.5 goals: 77%  ·  happens 86% of the time anyway
Torino v AS Roma17:30
HomeDrawAway
Model112168
Market162262
Over 2.5Under 2.5
Model5446
Market5446
Under 4.5 goals: 83%  ·  happens 86% of the time anyway
Model is 6 points above the market on away win (pinnacle). Worth a look at why.
Inter v Udinese19:45
HomeDrawAway
Model78157
Market77158
Over 2.5Under 2.5
Model6535
Market6436
Under 4.5 goals: 70%  ·  happens 86% of the time anyway
La Liga 2
Primeira Liga
Rio Ave v Estrela18:45
HomeDrawAway
Model372934
Market352935
Over 2.5Under 2.5
Model4951
Market4555
Under 4.5 goals: 88%  ·  happens 86% of the time anyway
Moreirense v Maritimo20:15
HomeDrawAway
Model403030
Market383032
Over 2.5Under 2.5
Model4357
Market4159
Under 4.5 goals: 91%  ·  happens 86% of the time anyway
SC Braga v Estoril20:45
HomeDrawAway
Model632412
Market672013
Over 2.5Under 2.5
Model4852
Market5545
Under 4.5 goals: 89%  ·  happens 86% of the time anyway
Super Lig
Gaziantep FK v Fenerbahçe18:00
HomeDrawAway
Model142066
Market162261
Over 2.5Under 2.5
Model6535
Market5545
Under 4.5 goals: 76%  ·  happens 86% of the time anyway

How the calls did

✓PSV Eindhoven 4–1 Sparta RotterdamPSV Eindhoven home win 83%
✓Galatasaray 1–0 KocaelisporGalatasaray home win 82%
✓Benfica 3–1 GIL VicenteBenfica home win 79%
✓PSV Eindhoven 4–1 Sparta Rotterdam over 2.5 goals 78%
✓Lille 2–0 Estac TroyesLille home win 76%
✓RB Leipzig 5–0 Hamburger SVRB Leipzig home win 76%
✓Benfica 3–1 GIL Vicente over 2.5 goals 75%
✓PEC Zwolle 0–7 FeyenoordFeyenoord away win 73%
✕Galatasaray 1–0 Kocaelispor over 2.5 goals 71%
✓RB Leipzig 5–0 Hamburger SV over 2.5 goals 71%
✓PEC Zwolle 0–7 Feyenoord over 2.5 goals 66%
✕Manchester United 0–1 Manchester City over 2.5 goals 64%
✓Tenerife 2–0 Leganes under 2.5 goals 64%
✓Levante 2–4 BarcelonaBarcelona away win 63%
✕Lille 2–0 Estac Troyes over 2.5 goals 63%
✓Getafe 1–1 Deportivo La Coruna under 2.5 goals 60%
✕Stade Brestois 29 0–1 Paris Saint Germain over 2.5 goals 60%
✕Valladolid 0–3 Oviedo under 2.5 goals 58%
✓Celta Vigo 1–1 Malaga under 2.5 goals 58%
✓Mallorca 2–0 Sabadell under 2.5 goals 56%
✕Gençlerbirliği S.K. 1–2 Kasımpaşa under 2.5 goals 56%
✓Sporting Gijon 0–1 Eldense under 2.5 goals 56%

16 of 22 settled since yesterday · 190 of 284 since the model went live.

Every match, for the record

The model rates the whole card, not just the calls, and learns from all of it. Judged as probabilities rather than picks — a 38% favourite losing is the model working, not failing.

·Resulttop pick right 17/26, we claimed 55% · 270/552 all-time
what actually happenedwe gave it 49% on average
·Over/under 2.5top pick right 15/26, we claimed 59% · 320/552 all-time
what actually happenedwe gave it 53% on average

A well-calibrated model's average claim matches how often it happens. That is the number Rule 9 gates on, and it is tracked for results and goals alike whether or not a fixture ever produced a call.

What these numbers are. The model's own estimate of how likely each result is, from form, Elo, rest, shots and xG as they stood at 06:00 UK on match day. One bivariate Poisson produces all of them, so the result and the goals figures share one underlying view of the match. Each published figure is then calibrated against what actually happened in past matches, one market at a time — so they agree closely but are not forced to agree exactly. Market figures are the bookmaker's prices with their margin removed, so the two are comparable.

What they are not. Across 57,633 out-of-sample fixtures the market separated matches better than the model in every league, every season, every outcome and every confidence band — 24 slices, no exceptions, re-tested in August 2026 on the current model. This is a second opinion, not an edge. Where it earns its keep is honesty about its own confidence: when it says 74%, that happens about 74% of the time.

Why a call appears. Thresholds — home 70% · away 60% · over 60% · under 55% — sit where the model has historically been as good as its claim. Raising them would surface fewer calls and be less accurate about them, because its confidence above those levels is inflated everywhere except home wins. Draws are never flagged: the highest one ever rated was 62%.

9 rated · 1 not rated · model goals_v7_cal · built 2026-09-14 07:05 UK