Football ratings

Friday 4 September 2026 · times UK

The model's strongest calls

79%FC Porto — home winFC Porto v Moreirense · 20:15 · market 82% · this strong, 82% land (2,727 cases)

£10 on all 1 as one multiple returns about £12 if every one lands. The model puts that at 79%, the market at 82%, and the price needs 85% 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.

71%Paris Saint Germain v Monaco — over 2.5 goals20:05 · market 67% · this strong, 76% land (485 cases)

65%VfB Stuttgart v 1. FC Köln — over 2.5 goals19:30 · market 70% · this strong, 66% land (4,584 cases)

63%Lyon v Auxerre — over 2.5 goals18:00 · market 57% · this strong, 66% land (4,584 cases)

63%Ipswich v Liverpool — over 2.5 goals20:00 · market 67% · this strong, 66% land (4,584 cases)

62%FC Porto v Moreirense — over 2.5 goals20:15 · market 58% · this strong, 66% land (4,584 cases)

56%Las Palmas v Leganes — under 2.5 goals19:30 · market 55% · this strong, 58% land (10,295 cases)

Every fixture

Premier League

Ipswich v Liverpool20:00

	Home	Draw	Away
Model	22	23	54
Market	17	19	64

	Over 2.5	Under 2.5
Model	63	37
Market	67	33

Under 4.5 goals: 77% · happens 86% of the time anyway

Model is 10 points below the market on away win (pinnacle). Worth a look at why.

La Liga

Real Betis v Real Madrid20:00

	Home	Draw	Away
Model	25	26	49
Market	14	18	68

	Over 2.5	Under 2.5
Model	53	47
Market	69	31

Under 4.5 goals: 84% · happens 86% of the time anyway

Model is 19 points below the market on away win (pinnacle). Worth a look at why.

Serie A

Genoa v Como19:45

	Home	Draw	Away
Model	18	25	57
Market	18	30	53

	Over 2.5	Under 2.5
Model	49	51
Market	41	59

Under 4.5 goals: 87% · happens 86% of the time anyway

Bundesliga

VfB Stuttgart v 1. FC Köln19:30

	Home	Draw	Away
Model	54	24	22
Market	64	19	17

	Over 2.5	Under 2.5
Model	65	35
Market	70	30

Under 4.5 goals: 77% · happens 86% of the time anyway

Model is 10 points below the market on home win (pinnacle). Worth a look at why.

Ligue 1

Lyon v Auxerre18:00

	Home	Draw	Away
Model	66	21	14
Market	64	21	15

	Over 2.5	Under 2.5
Model	63	37
Market	57	43

Under 4.5 goals: 77% · happens 86% of the time anyway

Paris Saint Germain v Monaco20:05

	Home	Draw	Away
Model	65	20	15
Market	70	17	12

	Over 2.5	Under 2.5
Model	71	29
Market	67	33

Under 4.5 goals: 69% · happens 86% of the time anyway

La Liga 2

Las Palmas v Leganes19:30

	Home	Draw	Away
Model	48	29	24
Market	46	30	23

	Over 2.5	Under 2.5
Model	44	56
Market	45	55

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

Eredivisie

Sparta Rotterdam v PEC Zwolle19:00

	Home	Draw	Away
Model	54	25	21
Market	49	24	26

	Over 2.5	Under 2.5
Model	56	44
Market	65	35

Under 4.5 goals: 84% · happens 86% of the time anyway

Primeira Liga

FC Porto v Moreirense20:15

	Home	Draw	Away
Model	79	15	5
Market	82	12	6

	Over 2.5	Under 2.5
Model	62	38
Market	58	42

Under 4.5 goals: 80% · happens 86% of the time anyway

Super Lig

Başakşehir v Galatasaray18:00

	Home	Draw	Away
Model	24	25	50
Market	19	21	60

	Over 2.5	Under 2.5
Model	58	42
Market	65	35

Under 4.5 goals: 82% · happens 86% of the time anyway

Model is 9 points below the market on away win (pinnacle). Worth a look at why.

How the calls did

✓Toulouse 0–1 Lille under 2.5 goals 58%

✓Real Sociedad 0–0 Celta Vigo under 2.5 goals 55%

2 of 2 settled since yesterday · 117 of 174 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 2/3, we claimed 41% · 163/323 all-time

what actually happenedwe gave it 37% on average

·Over/under 2.5top pick right 3/3, we claimed 55% · 191/323 all-time

what actually happenedwe gave it 55% 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%.

10 rated · 0 not rated · model goals_v7_cal · built 2026-09-04 07:04 UK