🤖 Model performance

AI Model Statistics

Our machine learning model analyses every football match it can find, not just the 3 tips we publish daily. Below you find the full performance data of the AI across thousands of matches. This is how the model learns and improves over time.
3,580Matches Analysed
3,222Settled
42.3%Model Accuracy
1,363Correct Predictions

This is the model's raw hit-rate on the exact 1X2 result across every match it analyses, not the win-rate of our published tips. Our tips combine multiple markets (double chance, over/under, Asian handicap) and win far more often. These figures are cumulative since March 2026 and include earlier model versions; our current model (v4) performs more strongly, see the Ensemble section below. See our tip results. What do these numbers mean?

Outcome Distribution

44%
26%
30%
Home Win 44% (1413)Draw 26% (853)Away Win 30% (956)

Over/Under 1.5 Distribution

78%
22%
Over 1.5 78% (2147)Under 1.5 22% (589)

O/U 1.5 Model Accuracy: 77.1% (2109/2736 correct)

Over/Under 2.5 Distribution

55%
45%
Over 2.5 55% (1770)Under 2.5 45% (1452)

O/U Model Accuracy: 54.2% (1747/3222 correct)

Over/Under 3.5 Distribution

33%
67%
Over 3.5 33% (894)Under 3.5 67% (1842)

O/U 3.5 Model Accuracy: 64.7% (1771/2736 correct)

Both Teams to Score (BTTS)

57%
43%
BTTS Yes 57% (1547)BTTS No 43% (1189)

BTTS Model Accuracy: 54.9% (1502/2736 correct)

Asian Handicap Results

48%
50%
2%
Home Covered 48% (1165)Away Covered 50% (1198)Push 2% (43)

AH Model Accuracy: 44% (1039/2363 correct, 43 push)

1X2 Model Accuracy by Competition

This is the raw 1X2 (home/draw/away) hit-rate of the model. Our published tips also use double chance, over/under and Asian-handicap markets, so their win-rate differs; see the archive for tip results.

Strong (45%+)Moderate (38-45%)Weak (below 38%)Dashed line = 33.3% (random pick)
CompetitionMatchesCorrectAccuracy
Serie A9053
58.9%+25.6
Eredivisie8243
52.4%+19.1
Super League6332
50.8%+17.5
Jupiler Pro League10350
48.5%+15.2
Primeira Liga9144
48.4%+15.1
Serie B8139
48.1%+14.8
3. Liga8139
48.1%+14.8
1. Division13163
48.1%+14.8
Ekstraklasa10951
46.8%+13.5
UEFA Europa Conference League247112
45.3%+12
Ligue 17534
45.3%+12
Allsvenskan13962
44.6%+11.3
2. Bundesliga8337
44.6%+11.3
Bundesliga6428
43.8%+10.5
Superliga7532
42.7%+9.4
La Liga10745
42.1%+8.8
Premier League288120
41.7%+8.4
Super League 15924
40.7%+7.4
League One12048
40%+6.7
Segunda División13954
38.8%+5.5

Recent AI Predictions

DateMatch1X2AIC O/U 1.5O/U 2.5O/U 3.5BTTSAH LineActualResult
25 Aug 2026UEFA Champions LeagueBodo/Glimt vs NEC NijmegenHome Win56%Over 1.5 ✅Over 2.5 ✅Over 3.5 ❌BTTS Yes ❌-0.8 (Home) ✅Home Win (3-0)✅
25 Aug 2026UEFA Champions LeagueLask Linz vs CelticHome Win46%Over 1.5 ✅Over 2.5 ✅Under 3.5 ❌BTTS No ❌-0.5 (Home) ✅Home Win (4-1)✅
25 Aug 2026La LigaValencia vs Real BetisHome Win38%—Over 2.5 ❌——+0.0 (Away)Away Win (0-1)❌
25 Aug 2026UEFA Champions LeagueSabah FA vs Hapoel Beer ShevaHome Win49%—Over 2.5 ✅——-0.5 (Home) ✅Home Win (3-2)✅
24 Aug 2026La LigaMalaga vs Deportivo La CorunaDraw63%—Under 2.5 ✅——+0.0 (Away)Draw (1-1)✅
24 Aug 2026Segunda DivisiónGranada CF vs MallorcaAway Win39%—Under 2.5 ✅——+0.0 (Away)Home Win (2-0)❌
24 Aug 2026Primeira LigaGIL Vicente vs Casa PiaHome Win48%—Under 2.5 ✅——-0.5 (Home) ✅Home Win (2-0)✅
24 Aug 2026Premier LeagueFulham vs ChelseaHome Win35%Over 1.5 ✅Over 2.5 ✅Under 3.5 ❌BTTS Yes ✅+0.0 (Away)Away Win (2-3)❌
24 Aug 2026Ligue 2Reims vs AnnecyAway Win69%Over 1.5 ✅Over 2.5 ✅Over 3.5 ✅BTTS Yes ✅+1.3 (Away) ❌Home Win (3-1)❌
24 Aug 2026Serie AAS Roma vs FiorentinaHome Win57%—Over 2.5 ✅——-0.8 (Home) ✅Home Win (4-0)✅
24 Aug 2026La LigaOsasuna vs LevanteHome Win40%Over 1.5 ❌Over 2.5 ❌Under 3.5 ✅BTTS Yes ❌-0.3 (Home) ❌Draw (0-0)❌
24 Aug 2026Serie ABologna vs LazioHome Win40%—Over 2.5 ❌——-0.3 (Home) ❌Away Win (0-1)❌
23 Aug 2026Primeira LigaFC Porto vs AroucaHome Win75%—Over 2.5 ❌——-1.5 (Home) ✅Home Win (2-0)✅
23 Aug 2026La LigaElche vs BarcelonaAway Win59%—Under 2.5 ❌——+1.0 (Away) ✅Away Win (0-5)✅
23 Aug 2026Segunda DivisiónTenerife vs AlmeriaHome Win54%—Over 2.5 ❌——-0.8 (Home) ✅Home Win (1-0)✅

Ensemble Model

42.2%Ensemble Accuracy
3,189Settled Matches

Our v4 GradientBoosting model — the AI behind every tip we publish — currently scores 46.2% accuracy on 1,353 settled matches since deployment. This is in line with the inherent difficulty of 3-way football outcomes (random = 33.3%). Accuracy will stabilise as more data accumulates.

35.1%When All Models Agree
1,038All Models Agreed

Ensemble Score Distribution & Accuracy

Score RangeMatchesAccuracy
0-9233
29.6%
10-191005
37.9%
20-29493
38.7%
30-39449
39.9%
40-49435
46.4%
50-59286
55.2%
60-69189
52.4%
70-7976
69.7%
80-8918
72.2%
90-994
25%
100-1091
100%

Model Calibration

Does a higher confidence score actually mean a more accurate prediction? This chart answers that. We group every settled prediction by the internal confidence score the model assigned, then show the real win-rate for each group. A rising staircase is what you want to see, it means the model knows when it is more likely to be right.

Each bar groups model predictions by internal confidence score (0–100). The height shows how often those predictions were actually correct on settled matches. A rising pattern means the model’s confidence is meaningful: higher scores genuinely correspond to more accurate predictions. Data covers our core leagues where the model has proven signal. Hover for sample sizes. This is the model’s internal ranking score across every match it analyses — not the per-tip AI Confidence shown on the tips and homepage.

Model accuracy is calculated on settled matches only. The current model uses form, goals average and H2H data as input features. Accuracy improves as more live data is collected.

More transparency: Tip results & track record · How accurate are AI predictions?