Football ratings

Monday 24 August 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.

60%AS Roma v Fiorentina — over 2.5 goals19:45 · market 49% · this strong, 66% land (4,584 cases)

56%Bologna v Lazio — under 2.5 goals17:30 · market 58% · this strong, 58% land (10,295 cases)

Every fixture

Premier League

Fulham v Chelsea20:00

	Home	Draw	Away
Model	38	29	33
Market	24	24	52

	Over 2.5	Under 2.5
Model	52	48
Market	57	43

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

Model is 14 points above the market on home win (pinnacle). Worth a look at why.

La Liga

Osasuna v Levante18:30

	Home	Draw	Away
Model	45	28	27
Market	53	26	21

	Over 2.5	Under 2.5
Model	49	51
Market	46	54

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

Model is 8 points below the market on home win (pinnacle). Worth a look at why.

Malaga v Deportivo La Coruna20:30

	Home	Draw	Away
Model	45	27	28
Market	40	32	28

	Over 2.5	Under 2.5
Model	51	49
Market	37	63

Under 4.5 goals: 85% · happens 86% of the time anyway

Serie A

Bologna v Lazio17:30

	Home	Draw	Away
Model	39	30	31
Market	43	30	27

	Over 2.5	Under 2.5
Model	44	56
Market	42	58

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

AS Roma v Fiorentina19:45

	Home	Draw	Away
Model	67	20	13
Market	56	25	19

	Over 2.5	Under 2.5
Model	60	40
Market	49	51

Under 4.5 goals: 76% · happens 86% of the time anyway

Model is 11 points above the market on home win (pinnacle). Worth a look at why.

La Liga 2

Celta de Vigo II v FC Andorra18:00

Not rated — Celta de Vigo II has 1 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.

Granada CF v Mallorca20:30

	Home	Draw	Away
Model	25	28	46
Market	30	32	38

	Over 2.5	Under 2.5
Model	45	55
Market	39	61

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

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

Primeira Liga

GIL Vicente v Casa Pia20:15

	Home	Draw	Away
Model	50	28	22
Market	56	26	18

	Over 2.5	Under 2.5
Model	46	54
Market	42	58

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

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

Super Lig

Kocaelispor v Amed19:30

Not rated — Amed has 1 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.

How the calls did

✓PSV Eindhoven 5–1 GroningenPSV Eindhoven home win 75%

✓Rennes 2–2 Paris Saint Germain over 2.5 goals 74%

✓FC Porto 2–0 AroucaFC Porto home win 74%

✓Manchester City 2–1 Bournemouth over 2.5 goals 71%

✓PSV Eindhoven 5–1 Groningen over 2.5 goals 71%

✓Manchester City 2–1 BournemouthManchester City home win 71%

✓Cambuur 2–5 Feyenoord over 2.5 goals 67%

✓Frosinone 0–1 JuventusJuventus away win 63%

✕Rennes 2–2 Paris Saint GermainParis Saint Germain away win 63%

✓Newcastle 2–2 Liverpool over 2.5 goals 62%

✓Tenerife 1–0 Almeria under 2.5 goals 62%

✕FC Porto 2–0 Arouca over 2.5 goals 62%

✓Cambuur 2–5 FeyenoordFeyenoord away win 62%

✓Santa Clara 1–0 Famalicao under 2.5 goals 62%

✓Angers 0–2 LilleLille away win 61%

✓Sporting Gijon 1–0 Burgos under 2.5 goals 60%

✓Venezia 0–2 Lecce under 2.5 goals 58%

✓Castellón 0–0 Sabadell under 2.5 goals 56%

✕Torino 1–2 AC Milan under 2.5 goals 55%

16 of 19 settled since yesterday · 68 of 106 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 19/28, we claimed 52% · 83/173 all-time

what actually happenedwe gave it 45% on average

·Over/under 2.5top pick right 22/28, we claimed 58% · 105/173 all-time

what actually happenedwe gave it 56% 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%.

7 rated · 2 not rated · model goals_v7_cal · built 2026-08-24 07:02 UK