Football ratings

Sunday 16 August 2026 · times UK

The model's strongest calls

75%Beşiktaş — home winBeşiktaş v Eyüpspor · 19:30 · market 68% · this strong, 77% land (1,215 cases)

65%Beşiktaş v Eyüpspor — over 2.5 goals19:30 · market 61% · this strong, 66% land (1,749 cases)

57%Famalicao v Maritimo — under 2.5 goals20:30 · market 56% · this strong, 57% land (7,790 cases)

£10 on all 3 as one multiple returns about £36 if every one lands. The model puts that at 28%, 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%.

Every fixture

La Liga 2

Las Palmas v Albacete20:30

	Home	Draw	Away
Model	40	29	31
Market	53	27	20

	Over 2.5	Under 2.5
Model	48	52
Market	48	52

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

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

Primeira Liga

Famalicao v Maritimo20:30

	Home	Draw	Away
Model	54	29	17
Market	54	27	19

	Over 2.5	Under 2.5
Model	42	57
Market	44	56

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

Super Lig

Amed v Erzurumspor FK19:30

Not rated — Amed has 0 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.

Beşiktaş v Eyüpspor19:30

	Home	Draw	Away
Model	75	15	10
Market	68	19	13

	Over 2.5	Under 2.5
Model	65	35
Market	61	39

Under 4.5 goals: 75% · happens 86% of the time anyway

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

How the calls did

✕Feyenoord 2–2 GO Ahead EaglesFeyenoord home win 79%

✕Ajax 2–2 HeerenveenAjax home win 75%

✓Excelsior 1–2 PSV EindhovenPSV Eindhoven away win 71%

✓Excelsior 1–2 PSV Eindhoven over 2.5 goals 71%

✕Gençlerbirliği S.K. 2–1 FenerbahçeFenerbahçe away win 68%

✓Utrecht 1–4 AZ Alkmaar over 2.5 goals 65%

✓Feyenoord 2–2 GO Ahead Eagles over 2.5 goals 65%

✓Ajax 2–2 Heerenveen over 2.5 goals 65%

✓Racing Santander 2–2 Villarreal over 2.5 goals 64%

✓Burton Albion 1–1 Stevenage under 2.5 goals 61%

✕Cambridge United 3–2 Wigan under 2.5 goals 61%

✓Willem II 1–4 NEC Nijmegen over 2.5 goals 61%

✓Twente 3–1 PEC Zwolle over 2.5 goals 61%

✕Portsmouth 1–3 QPR under 2.5 goals 60%

✕Alaves 3–0 Getafe under 2.5 goals 60%

✓Notts County 1–1 Leicester under 2.5 goals 58%

✓Bradford 2–0 Peterborough under 2.5 goals 58%

✓Blackpool 1–1 Wycombe under 2.5 goals 58%

✕Mansfield Town 2–1 Doncaster under 2.5 goals 58%

✓Kasımpaşa 1–1 Trabzonspor under 2.5 goals 58%

✕Sevilla 2–1 Rayo Vallecano under 2.5 goals 58%

✕Eibar 1–3 Tenerife under 2.5 goals 58%

✕Leyton Orient 1–2 Sheffield Wednesday under 2.5 goals 57%

✕Alverca 2–2 Estrela under 2.5 goals 57%

✕Charlton 2–1 Derby under 2.5 goals 55%

13 of 25 settled since yesterday · 28 of 51 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 18/43, we claimed 47% · 32/76 all-time

what actually happenedwe gave it 36% on average

·Over/under 2.5top pick right 28/43, we claimed 57% · 44/76 all-time

what actually happenedwe gave it 52% 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.

Changed after we rated them

⚠SC Braga v GIL Vicentepostponed — our rating is void

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 come off a single scoreline distribution and cannot contradict each other. 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%.

3 rated · 1 not rated · model goals_v3_cal · built 2026-08-16 18:08 UK