Football ratings

Tuesday 1 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.

56%Lincoln v Blackburn — under 2.5 goals19:45 · market 50% · this strong, 58% land (10,295 cases)

Every fixture

Championship

Lincoln v Blackburn19:45

	Home	Draw	Away
Model	40	30	30
Market	41	28	31

	Over 2.5	Under 2.5
Model	44	56
Market	50	50

Under 4.5 goals: 91% · happens 86% of the time anyway

Portsmouth v Derby19:45

	Home	Draw	Away
Model	47	27	26
Market	43	29	29

	Over 2.5	Under 2.5
Model	51	49
Market	47	53

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

Preston v Bristol City19:45

	Home	Draw	Away
Model	38	29	33
Market	36	28	36

	Over 2.5	Under 2.5
Model	48	52
Market	50	50

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

Sheffield Utd v Bolton19:45

	Home	Draw	Away
Model	40	28	31
Market	56	25	19

	Over 2.5	Under 2.5
Model	50	50
Market	50	50

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

Model is 16 points below the market on home win (pinnacle). Worth a look at why.

Swansea v Watford19:45

	Home	Draw	Away
Model	57	25	19
Market	50	26	24

	Over 2.5	Under 2.5
Model	53	47
Market	50	50

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

Model is 7 points above the market on home win (pinnacle). Worth a look at why.

West Ham v Wolves19:45

	Home	Draw	Away
Model	46	26	28
Market	47	26	27

	Over 2.5	Under 2.5
Model	56	44
Market	54	46

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

Birmingham v Southampton20:00

	Home	Draw	Away
Model	34	27	38
Market	38	28	34

	Over 2.5	Under 2.5
Model	53	47
Market	52	48

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

Stoke City v Norwich20:00

	Home	Draw	Away
Model	30	29	42
Market	30	27	43

	Over 2.5	Under 2.5
Model	48	52
Market	52	48

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

League One

Bradford v Cambridge United19:45

	Home	Draw	Away
Model	41	30	29
Market	53	25	22

	Over 2.5	Under 2.5
Model	45	55
Market	51	49

Under 4.5 goals: 91% · happens 86% of the time anyway

Model is 12 points below the market on home win (pinnacle). Worth a look at why.

Bromley v Leyton Orient19:45

Not rated — Bromley has 3 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.

Doncaster v Notts County19:45

	Home	Draw	Away
Model	41	28	31
Market	46	27	27

	Over 2.5	Under 2.5
Model	54	46
Market	49	51

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

Huddersfield v Oxford United19:45

	Home	Draw	Away
Model	39	29	32
Market	56	24	20

	Over 2.5	Under 2.5
Model	49	51
Market	55	45

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

Model is 18 points below the market on home win (pinnacle). Worth a look at why.

Leicester v Plymouth19:45

	Home	Draw	Away
Model	47	27	25
Market	50	24	27

	Over 2.5	Under 2.5
Model	53	47
Market	57	43

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

Peterborough v Stevenage19:45

	Home	Draw	Away
Model	38	30	32
Market	37	28	35

	Over 2.5	Under 2.5
Model	46	54
Market	48	52

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

Wycombe v Sheffield Wednesday19:45

	Home	Draw	Away
Model	39	27	35
Market	37	26	37

	Over 2.5	Under 2.5
Model	58	42
Market	55	45

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

How the calls did

✓Barcelona 5–2 Rayo VallecanoBarcelona home win 83%

✓Benfica 2–1 Estoril over 2.5 goals 78%

✓Benfica 2–1 EstorilBenfica home win 75%

✓Barcelona 5–2 Rayo Vallecano over 2.5 goals 69%

✕Lecce 0–4 AS Roma under 2.5 goals 57%

✓Osasuna 1–0 Getafe under 2.5 goals 57%

✕Burgos 2–2 Real Sociedad II under 2.5 goals 56%

5 of 7 settled since yesterday · 110 of 165 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 7/8, we claimed 56% · 146/292 all-time

what actually happenedwe gave it 55% on average

·Over/under 2.5top pick right 4/8, we claimed 60% · 177/292 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%.

14 rated · 1 not rated · model goals_v7_cal · built 2026-09-01 07:04 UK