Football ratings

Monday 7 September 2026 · times UK

The model's strongest calls

Nothing clears the bar today. The thresholds are set where the model has historically been as good as it claims — home win 70%, away win 60% — and a quiet day is a real answer, not a gap.

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.

66%Getafe v Celta Vigo — under 2.5 goals18:00 · market 69% · this strong, 55% land (156 cases)

64%Sabadell v Cordoba — under 2.5 goals19:30 · market 54% · this strong, 61% land (2,190 cases)

56%Estoril v Arouca — under 2.5 goals20:15 · market 49% · this strong, 58% land (10,295 cases)

Every fixture

League One

Bromley v AFC Wimbledon20:00

Not rated — Bromley has 4 prior matches in the store, most likely promoted from a division we do not collect. A rating built on that would be a guess wearing a percentage.

La Liga

Getafe v Celta Vigo18:00

	Home	Draw	Away
Model	34	33	32
Market	38	34	28

	Over 2.5	Under 2.5
Model	34	66
Market	31	69

Under 4.5 goals: 95% · happens 86% of the time anyway

Elche v Real Sociedad20:30

	Home	Draw	Away
Model	36	29	35
Market	30	27	43

	Over 2.5	Under 2.5
Model	48	52
Market	54	46

Under 4.5 goals: 88% · happens 86% of the time anyway

Model is 6 points above the market on home win (pinnacle). Worth a look at why.

Serie A

Cagliari v Lecce17:30

	Home	Draw	Away
Model	52	27	22
Market	48	30	22

	Over 2.5	Under 2.5
Model	49	51
Market	39	61

Under 4.5 goals: 86% · happens 86% of the time anyway

Udinese v Lazio19:45

	Home	Draw	Away
Model	30	29	40
Market	33	32	35

	Over 2.5	Under 2.5
Model	45	55
Market	40	60

Under 4.5 goals: 89% · happens 86% of the time anyway

La Liga 2

Sabadell v Cordoba19:30

	Home	Draw	Away
Model	41	32	27
Market	45	29	26

	Over 2.5	Under 2.5
Model	36	64
Market	46	54

Under 4.5 goals: 94% · happens 86% of the time anyway

Primeira Liga

Estoril v Arouca20:15

	Home	Draw	Away
Model	33	30	38
Market	40	28	32

	Over 2.5	Under 2.5
Model	44	56
Market	51	49

Under 4.5 goals: 90% · happens 86% of the time anyway

Super Lig

Göztepe v Gaziantep FK18:00

	Home	Draw	Away
Model	49	26	25
Market	49	27	24

	Over 2.5	Under 2.5
Model	56	44
Market	53	47

Under 4.5 goals: 83% · happens 86% of the time anyway

Rizespor v Alanyaspor18:00

	Home	Draw	Away
Model	46	28	27
Market	51	28	22

	Over 2.5	Under 2.5
Model	51	49
Market	49	51

Under 4.5 goals: 86% · happens 86% of the time anyway

How the calls did

✓Arsenal 2–1 ChelseaArsenal home win 73%

✓Heart Of Midlothian 2–1 DundeeHeart Of Midlothian home win 70%

✓Valencia 0–5 BarcelonaBarcelona away win 67%

✓Everton 2–2 Manchester United over 2.5 goals 66%

✓Estac Troyes 2–6 Strasbourg over 2.5 goals 64%

✓Groningen 2–2 Twente over 2.5 goals 63%

✕Santa Clara 4–0 Rio Ave under 2.5 goals 62%

✓Eintracht Frankfurt 1–4 FC Augsburg over 2.5 goals 62%

✓Marseille 2–3 Paris FC over 2.5 goals 61%

✓Heerenveen 2–3 AZ Alkmaar over 2.5 goals 61%

✕Alaves 5–2 Osasuna under 2.5 goals 61%

✓Heart Of Midlothian 2–1 Dundee over 2.5 goals 60%

✓Angers 1–2 Rennes over 2.5 goals 60%

✓Oviedo 0–0 Burgos under 2.5 goals 58%

✕Birmingham 2–2 Wolves under 2.5 goals 55%

12 of 15 settled since yesterday · 148 of 220 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 15/30, we claimed 51% · 209/422 all-time

what actually happenedwe gave it 41% on average

·Over/under 2.5top pick right 21/30, we claimed 57% · 249/422 all-time

what actually happenedwe gave it 54% 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%.

8 rated · 1 not rated · model goals_v7_cal · built 2026-09-07 07:04 UK