Football ratings

Sunday 4 October 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%Castellón v AD Ceuta FC — over 2.5 goals17:30 · market 70% · this strong, 66% land (4,584 cases)
56%Girona v Mallorca — under 2.5 goals20:00 · market 48% · this strong, 58% land (10,295 cases)

Every fixture

La Liga 2
Real Sociedad II v Granada CF13:00
HomeDrawAway
Model342937
Market362935
Over 2.5Under 2.5
Model4753
Market4951
Under 4.5 goals: 88%  ·  happens 86% of the time anyway
Sporting Gijon v Celta de Vigo II15:15
HomeDrawAway
Model542719
Market612217
Over 2.5Under 2.5
Model4753
Market5644
Under 4.5 goals: 88%  ·  happens 86% of the time anyway
Model is 7 points below the market on home win (pinnacle). Worth a look at why.
Castellón v AD Ceuta FC17:30
HomeDrawAway
Model692011
Market78148
Over 2.5Under 2.5
Model6040
Market7030
Under 4.5 goals: 79%  ·  happens 86% of the time anyway
Model is 9 points below the market on home win (pinnacle). Worth a look at why.
Las Palmas v Valladolid17:30
HomeDrawAway
Model492724
Market432929
Over 2.5Under 2.5
Model4951
Market4753
Under 4.5 goals: 87%  ·  happens 86% of the time anyway
Model is 6 points above the market on home win (pinnacle). Worth a look at why.
Girona v Mallorca20:00
HomeDrawAway
Model423029
Market412831
Over 2.5Under 2.5
Model4456
Market5248
Under 4.5 goals: 90%  ·  happens 86% of the time anyway

How the calls did

✕Albacete 1–3 Eibar under 2.5 goals 61%
✕Almeria 2–1 Burgos under 2.5 goals 56%

0 of 2 settled since yesterday · 232 of 351 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 3/6, we claimed 45% · 338/712 all-time
what actually happenedwe gave it 37% on average
·Over/under 2.5top pick right 2/6, we claimed 54% · 405/712 all-time
what actually happenedwe gave it 47% 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%.

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