Home win
76.36%
SL Benfica
POR1 · Primeira Liga · Match Analysis
SL Benfica vs
Vitória Guimarães
Model-based match probabilities derived from multi-season xG data, team strength, venue performance, recent form, Elo ratings and league context.
Model output
Match probabilities.
Probabilities are model estimates, not certainties or betting guarantees.
Draw
15.42%
X
Away win
8.22%
Vitória Guimarães
Score model
Most likely scorelines.
Exact-score probabilities from the Poisson + Dixon-Coles goal model.
Additional scorelines
4:06.47%
1:06.29%
4:15.68%
2:23.82%
5:03.62%
Team context
Strength and recent form.
Venue-adjusted team strength, Elo rating and recent xG performance.
Home
SL Benfica
Elo1686.5
Overall attack2.18
Overall defense0.81
Home attack2.48
Home defense0.73
Form signal+1.305
Last 5 xGF / xGA2.12 / 0.91
Last 10 xGF / xGA2.37 / 0.89
Last 10 xGD+1.48
League statusSTABLE · from POR1 2025/26
Away
Vitória Guimarães
Elo1470.6
Overall attack1.38
Overall defense1.24
Away attack1.23
Away defense1.59
Form signal+0.861
Last 5 xGF / xGA1.76 / 0.82
Last 10 xGF / xGA1.66 / 0.96
Last 10 xGD+0.70
League statusSTABLE · from POR1 2025/26
Elo difference
+215.9
Elo is one input among several and does not determine the final 1X2 probability on its own.
Head-to-head
Historical matchup context.
H2H values provide context and are not used as a standalone prediction.
Goal distribution
Total goals profile.
The model's probability distribution for the total number of goals.
03.35%
17.70%
217.94%
320.98%
419.27%
514.16%
68.67%
7+7.94%
Technical detail
How the model reached the estimate.
Detailed diagnostics are kept below the headline probabilities so the public report remains readable.
League baseline and model setup
LeaguePOR1
Loaded teams26
Loaded historical matches1286
Target season2026/27
Previous seasons in history4
Season window2022/23 → 2023/24 → 2024/25 → 2025/26 → 2026/27
League tierTier 1
Historical league matches1286
xG matches368 / 1286
Effective xG matches294.02
Observed home xG1.44
Observed away xG1.21
Model home xG baseline1.44
Model away xG baseline1.21
Total league xG baseline2.65
Home-advantage weight1.000
Model configdata/models/POR1.json
Team attack half-life240.0 days
Team defense half-life240.0 days
Attack strength weight1.000
Defense strength weight1.000
Venue prior matches0.00
DistributionPoisson + Dixon-Coles
Dixon-Coles rho-0.130 (effective -0.130)
Dixon-Coles decay0.000
Goal overdispersion0.000
Implied goal variance H / A2.80 / 0.88
Relative strengths and form diagnostics
SL Benfica
Home attack strength1.486
Home defense weakness0.731
Base lambda home2.29
Attack form xGF level2.210
Defense form xGA level (lower is better)0.906
Opponent-adjusted attack residual+0.855
Opponent-adjusted defense residual (higher is better)+0.393
Opponent-adjustment weight0.000
Model attack signal+0.885
Model defense signal+0.420
Opponent blend0.000
Form matches 5 / 105 / 10
Last 5 xGF / xGA / xGD2.12 / 0.91 / +1.21
Last 10 xGF / xGA / xGD2.37 / 0.89 / +1.48
Vitória Guimarães
Away attack strength1.013
Away defense weakness1.068
Base lambda away0.90
Attack form xGF level1.726
Defense form xGA level (lower is better)0.866
Opponent-adjusted attack residual+0.384
Opponent-adjusted defense residual (higher is better)+0.446
Opponent-adjustment weight0.000
Model attack signal+0.401
Model defense signal+0.460
Opponent blend0.000
Form matches 5 / 105 / 10
Last 5 xGF / xGA / xGD1.76 / 0.82 / +0.95
Last 10 xGF / xGA / xGD1.66 / 0.96 / +0.70
Historical data coverage
SL Benfica
Total matches143
Home / away matches71 / 72
xG matches41 / 143
xG home / away coverage20 / 71 · 21 / 72
Effective total21.86
Effective attack / defense21.86 / 21.86
Effective home matches10.37
Effective home attack / defense10.37 / 10.37
Vitória Guimarães
Total matches143
Home / away matches72 / 71
xG matches41 / 143
xG home / away coverage21 / 72 · 20 / 71
Effective total21.76
Effective attack / defense21.76 / 21.76
Effective away matches10.54
Effective away attack / defense10.54 / 10.54
Historical data coverage
61.40%
This measures usable historical evidence. It is not the probability that the prediction is correct.
Validation
Historical model performance.
Leakage-safe backtesting compares the fitted model with a league baseline over 1266 historical matches.
Positive improvement means the model performed better than the league baseline.
Total goals log-loss vs baseline+0.24%
1X2 log-loss vs baseline+4.98%
BTTS Brier vs baseline+0.16%
Over 2.5 Brier vs baseline+1.40%
Full backtest metrics
Model
MAE total goals1.2923
Exact score log-loss2.9441
Total goals Brier0.8262
Total goals log-loss1.8573
1X2 Brier0.6154
1X2 log-loss1.0253
BTTS Brier0.2533
Over 1.5 Brier0.1973
Over 2.5 Brier0.2470
Over 3.5 Brier0.2062
League baseline
MAE total goals1.3075
Exact score log-loss3.0174
Total goals Brier0.8282
Total goals log-loss1.8617
1X2 Brier0.6525
1X2 log-loss1.0790
BTTS Brier0.2537
Over 1.5 Brier0.1984
Over 2.5 Brier0.2505
Over 3.5 Brier0.2073
Calibration diagnostics
Home win · ECE 10.54%
0- 10% n=9 avg= 6.2% actual= 33.3% 10- 20% n=51 avg= 16.0% actual= 17.6% 20- 30% n=39 avg= 25.6% actual= 23.1% 30- 40% n=324 avg= 37.2% actual= 22.8% 40- 50% n=731 avg= 42.5% actual= 53.2% 50- 60% n=58 avg= 54.7% actual= 53.4% 60- 70% n=25 avg= 65.2% actual= 68.0% 70- 80% n=23 avg= 75.0% actual= 87.0% 80- 90% n=6 avg= 82.0% actual= 83.3%
Draw · ECE 4.53%
10- 20% n=44 avg= 16.7% actual= 13.6% 20- 30% n=1134 avg= 28.5% actual= 23.8% 30- 40% n=88 avg= 31.3% actual= 34.1%
Away win · ECE 11.26%
0- 10% n=30 avg= 7.2% actual= 0.0% 10- 20% n=62 avg= 15.5% actual= 6.5% 20- 30% n=599 avg= 27.9% actual= 19.7% 30- 40% n=475 avg= 32.3% actual= 47.8% 40- 50% n=36 avg= 44.7% actual= 41.7% 50- 60% n=31 avg= 53.9% actual= 41.9% 60- 70% n=24 avg= 65.1% actual= 87.5% 70- 80% n=7 avg= 75.5% actual= 57.1% 80- 90% n=2 avg= 85.6% actual= 50.0%
BTTS · ECE 5.49%
30- 40% n=5 avg= 36.6% actual= 40.0% 40- 50% n=149 avg= 46.5% actual= 47.7% 50- 60% n=1090 avg= 54.9% actual= 48.9% 60- 70% n=22 avg= 61.4% actual= 50.0%
Over 2.5 · ECE 2.67%
30- 40% n=33 avg= 37.4% actual= 36.4% 40- 50% n=973 avg= 48.7% actual= 48.3% 50- 60% n=219 avg= 52.8% actual= 65.8% 60- 70% n=37 avg= 63.7% actual= 67.6% 70- 80% n=4 avg= 72.3% actual= 75.0%
Walk-forward - latest periods
| Period | N | Model 1X2 LL | Baseline 1X2 LL | Improvement |
|---|---|---|---|---|
| 2025-08 | 34 | 1.1609 | 1.2374 | +6.18% |
| 2025-09 | 29 | 1.0040 | 1.0960 | +8.39% |
| 2025-10 | 19 | 0.9447 | 1.0662 | +11.39% |
| 2025-11 | 25 | 0.9458 | 1.1352 | +16.69% |
| 2025-12 | 35 | 0.9457 | 1.0913 | +13.34% |
| 2026-01 | 33 | 0.8697 | 1.0548 | +17.55% |
| 2026-02 | 37 | 0.8835 | 1.0452 | +15.47% |
| 2026-03 | 29 | 1.0190 | 1.1271 | +9.59% |
| 2026-04 | 38 | 0.9623 | 1.0754 | +10.52% |
| 2026-05 | 27 | 1.0726 | 1.0879 | +1.40% |
| 2026-08 | 33 | 0.9133 | 1.0818 | +15.58% |
| 2026-09 | 29 | 1.0078 | 1.1078 | +9.02% |
Football is data.
NILYTIX turns match data into transparent model probabilities and measurable analytical signals.