Group G · Matchday 3

BelgiumvsNew Zealand

2026-06-26·20:00 localPredictions finalised

Snapshot · 2026-07-14Model 1.0.0Final prediction · locked 27 Jun, 01:23 UTCBelgium·New Zealand·Head-to-head →·
Full time · forecast gradedBelgium 5 1 New ZealandThe locked pre-match forecast has been graded against this result.See the calibration recap →

The forecast

Match-outcome probability

  • Belgium win
    63.9%
  • Draw
    22.2%
  • New Zealand win
    13.9%

The model rates Belgium as favourites at 83%, with New Zealand projected at 1% to win.

Rank checkFIFA ranks New Zealand #86 in the world; the model ranks them #42 in this tournament field, 44 places higher than the FIFA list suggests. All 48 compared →
Likeliest score2–016.7%
First goal0-15'38.8%
Both teams score32.3%
Over 2.5 goals56.5%
Top scorerWood13.4%
Expected goals2.5 - 0.4
Loading pitch visualisation...

Why the model says this

Favoring Belgium

  • ·Belgium holds a significant Elo gap of 282 points over New Zealand, indicating a substantial difference in team strength.
  • ·Belgium is ranked 8th globally by FIFA, significantly higher than New Zealand's 86th position.
  • ·The model projects Belgium to score 2.35 expected goals compared to New Zealand's 0.45 expected goals, suggesting a dominant attacking performance.
  • ·Individual models consistently favour Belgium, with the stacking model predicting an 88.7% chance of a home win and the DC model at 79.6%.

Favoring New Zealand

  • ·New Zealand recently secured a 4-1 victory in a FIFA Series match in March 2026.
  • ·They achieved a 1-1 draw in a friendly match in October 2025.

What the model can't fully price

  • ·The model does not account for the 4 players across both squads carrying fitness doubts, including 2 projected starters, as its lineup channel currently contributes zero.

Form check

Belgium

Steady

Belgium enters this match undefeated in their last six outings, securing three wins and three draws. Their recent form includes a dominant 5-2 victory in a friendly and a 7-0 win in World Cup qualification, demonstrating strong attacking capabilities.

Undefeated in their last 6 matches (3W, 3D).

New Zealand

Declining

New Zealand's recent form shows a struggle for consistency, with four losses in their last six matches. While they did achieve a 4-1 victory in the FIFA Series, this is offset by multiple defeats, including a 0-2 loss in the same series.

Four losses in their last 6 matches.

Analysis

How it plays out

Both sides run a balanced system, so this becomes a test of who executes the same ideas better on the day. Belgium will expect to hold 54% possession. New Zealand need their shape to stay compact without the ball and be clinical when they win it back.

What decides it

Chris Wood carries the marginally higher scoring probability (13.4% vs 6.9%).

Off the pitch

No major off-pitch asymmetries. This one is decided by the football.

The angle

The model gives New Zealand just 9.0% to win. Every World Cup produces group-stage upsets; the question is whether this fixture is one of them.

Goals & scorelines

Likeliest score 2–0 (16.7%) · xG 2.5 - 0.4

Expected goals

Belgium
2.52
New Zealand
0.43

Mean of the Dixon-Coles joint goal distribution. Same fit that produces the most-likely-scoreline list below.

Most likely scorelines

  • 2–0
    16.7%
  • 3–0
    14.0%
  • 1–0
    12.9%
  • 4–0
    8.8%
  • 2–1
    7.1%

From the Dixon-Coles joint Poisson with the low-score correction. Scorelines are listed in probability order; this is a description of the model's distribution, not a recommendation.

Most likely half-time scorelines

  • 1–0
    28.5%
  • 0–0
    23.3%
  • 2–0
    18.2%
  • 3–0
    7.6%
  • 1–1
    6.5%

Same Dixon-Coles fit as the full-time list above, with rates halved to a 45-minute window and the low-score correction applied to that 1st-half block. The 0-0 row sits higher here than at full-time because fewer minutes have elapsed.

Goal totals

  • More than 0.5 goals
    94.4%
  • More than 1.5 goals
    79.6%
  • More than 2.5 goals
    56.5%
  • More than 3.5 goals
    34.1%
  • More than 4.5 goals
    17.6%
  • More than 5.5 goals
    7.9%
  • Both teams score
    32.3%

Each row is the probability the match finishes with more than the listed number of goals. Both-teams-to-score is the probability each side scores at least once. All values are marginals of the Dixon-Coles joint goal grid that produces the scoreline list above — not market lines or any other operator construct.

Event-typed probabilities

  • Belgium clean sheetOpposing team scores zero65.3%
  • New Zealand clean sheetOpposing team scores zero8.0%

Derived from the same Dixon-Coles joint distribution as the scoreline list. These are descriptive event probabilities — see CLAUDE.md §3/§4 (formerly COMPLIANCE.md §4.2.7) for the framing the project uses.

Win-margin probability

  • Belgium by 4+
    19.5%
  • Belgium by 3+
    37.7%
  • Belgium by 2+
    61.2%
  • Belgium by 1+
    82.6%
  • Draw
    13.3%
  • New Zealand by 1+
    4.1%
  • New Zealand by 2+
    0.8%
  • New Zealand by 3+
    0.1%
  • New Zealand by 4+
    <0.1%

Each row is the probability the match ends with the listed margin or larger in that direction. Marginal of the Dixon-Coles joint goal grid; the “by 1+” rows plus the draw row sum to 1.

How the match unfolds

Over 2.5 goals 56.5% · BTTS 32.3%

Game state through the match

0%25%50%75%100%0'15'30'45'60'75'90'
  • Belgium ahead83.0%
  • Level12.6%
  • New Zealand ahead4.4%

Probability of each game state at minutes 0, 15, 30, 45, 60, 75, 90 — derived from two independent thinned-Poisson processes with the Dixon-Coles per-team rates. The three lines always sum to 1 at each minute. The right column shows the state at the match's closing minute.

When the first goal arrives

  • 0–15
    38.8%
  • 15–30
    23.8%
  • 30–45
    14.5%
  • 45–60
    8.9%
  • 60–75
    5.4%
  • 75–90
    3.3%
  • No goal
    5.3%

Probability the match's first goal arrives in each 15-minute window. Homogeneous Poisson with combined rate λ = λh + λa from the Dixon-Coles fit; the seven rows (six windows + no-goal tail) sum to 1.

Half-time / full-time grid

Joint probability of half-time and full-time results
HT ↓ / FT →HBelgium winDDrawANew Zealand win
HBelgium ahead61.8%1.9%0.2%
DLevel19.5%8.9%1.9%
ANew Zealand ahead1.7%1.8%2.3%

Each cell is P(half-time result, full-time result). All nine cells sum to 1. Derived from a halved-λ Dixon-Coles fit for the first half plus an independent-Poisson second-half convolution.

Comeback probability

  • Belgium trail at HT, avoid defeat at FT
    3.5%
  • New Zealand trail at HT, avoid defeat at FT
    2.1%

Joint probability — P(side trailing at half-time AND avoiding defeat at full-time). NOT conditional on trailing at HT. Derived from the same half-time / full-time decomposition that produces the HT/FT grid above; a tied first half is neither a home nor an away comeback opportunity.

Cards

  • Expected yellow cardsMean of the Poisson on total yellow cards.3.45
  • Total yellows over 2.567.0%
  • Total yellows over 3.545.3%
  • Total yellows over 4.526.5%
  • Any red cardP(at least one red card in the match).9.5%

Referee not yet assigned. Using the 2026 pool-mean per-match rate as a placeholder; the model picks up the referee's personal rate once the assignment is published. Total yellow cards modelled as a Poisson with mean equal to two team baselines plus the referee's deviation from the pool mean. Reds are modelled the same way, independently. See /docs/methodology/.

Teams & players

Top scorer: Wood (13.4%)

Match detail

Belgium

Model-rated key players: Kevin De Bruyne (MF) — P(scores) 6.9%; Loïs Openda (FW) — P(scores) 4.9%; Leandro Trossard (FW) — P(scores) 3.1%.

How they play

Belgium under Rudi Garcia play a balanced game, holding 54% of the ball — among the highest in the tournament field. Their likely shape is a other, though they have also used 4-2-3-1. They apply moderate pressing intensity (PPDA 23.1) and build patiently through midfield with 7.7 passes per attacking sequence.

What they must execute

Belgium will need to leverage their strengths while managing the physical demands of a tournament spread across three host countries. Managing minutes for Axel Witsel across what could be seven matches will test the coaching staff's rotation planning.

Storylines
Strong in goal: Thibaut Courtois#2 starting-GK rating in the field — 0.99 on club-derived save metrics across 48 teams.
Last dance: Axel Witsel37 at kickoff with 136 caps — probably his final World Cup.
Touchline: Rudi GarciaFirst World Cup as head coach, appointed 2025.

New Zealand

Model-rated key players: Chris Wood (FW) — P(scores) 13.4%; Ben Waine (FW) — P(scores) 4.4%; Kosta Barbarouses (FW) — P(scores) 4.4%.

How they play

Limited recent tournament data is available for New Zealand's tactical profile. Early indicators suggest a balanced approach.

What they must execute

New Zealand will need to leverage their strengths while managing the physical demands of a tournament spread across three host countries.

Storylines
Model bold: Model rates them #38 by tournament-winner probability — 48 places higher than FIFA #86.
Minutes load: XI averaged 2,624 club minutes in 2024-25 — #1 of 43 in the field. Heavy pre-tournament load on the starting eleven.
Club core: 5 of 24 predicted-squad players play their club football for Auckland FC — a single-club spine on the international side.
Set-piece outlook

Belgium historically converts 14.6% of xG from set-pieces, contributing 0.37 expected set-piece goals in this fixture. New Zealand converts 6.0% from set-pieces (0.03 expected). Combined, the model expects 0.40 set-piece goals across the 90 minutes.

  • P(Belgium scores set-piece goal) 30.9%
  • P(New Zealand scores set-piece goal) 2.6%
  • P(set-piece goal in match) 32.6%

Belgium: Kevin De Bruyne on corners (25 corners), Axel Witsel on free kicks (per fbref 2022 23)

Penalty outlook

If a penalty is awarded to Belgium, the model gives 71.4% conversion, 76.0% for New Zealand.

Belgium primary PK: Kevin De Bruyne (2/3 in 2020-21, per fbref 2022 23) · New Zealand primary PK: Chris Wood (1/1 in 2021-22, per fbref 2021 22).

Derived from the model's per-fixture forecast joint and supporting reference data (predicted squads, set-piece xG share, PK posteriors, club minutes). See /docs/methodology/ for the full methodology.

Tactical forecast

Belgiumbalanced
PPDA
23.1
Possession
54%
Directness (yds/pass)
5.0
Long balls/90
32
Set-piece xG
15%
New Zealandbalanced

Partial coverage from FotMob match stats (recent qualifiers and friendlies): possession and shot volume only. Press and build-up metrics are not available for this side.

PPDA
Possession
44%
Directness (yds/pass)
Long balls/90
Set-piece xG
6%

Style profile per side from StatsBomb open-data aggregation across recent international tournaments (Euro 2020/2024, Copa America 2024, AFCON 2023, World Cup 2018/2022). The tactical-fingerprint badge maps each team’s observed style vector into one of eight canonical archetypes via a rule-based classifier; teams with fewer than three matches of qualifying coverage carry an “insufficient-data” label rather than being forced into a default. Sides outside the StatsBomb-open corpus use FotMob team match stats from recent qualifiers and friendlies instead (possession and shot volume only), marked as partial coverage. PPDA = passes the side allows per defensive action (lower = more intense press). Formation distributions are not yet produced — that head of the §2.7 classifier is pending its own data pull. See /docs/methodology/.

Squad depth

Most irreplaceable starters

Belgium

  1. Youri TielemansCentral midfieldNo natural backup0.41gap
  2. Romelu LukakuStrikerNo natural backup0.37gap
  3. Zeno DebastCentre-backCover: Brandon Mechele · 0.560.32gap

New Zealand

  1. Marko StamenićCentral midfieldCover: Lachlan Bayliss · 0.000.58gap
  2. Chris WoodStrikerNo natural backup0.45gap
  3. Liberato CacaceFull-backCover: Ben Old · 0.280.26gap

Gap = how far a side's rating at the position falls from the starter to his likely in-squad replacement (named under each name). Larger = harder to replace. Descriptive metric, does not feed the published probabilities. Methodology →

Match conditions

  • AltitudeNear sea level3 m
  • Avg temperatureFive-year mean over the tournament window17.4 °C
  • Avg humidity73%
  • Heat stressShade WBGT ~19.5 °CLow heat stress
  • Pitch surfacetemporary natural grass over artificial turf

Artificial-turf stadium with a retractable roof; a temporary natural-grass pitch is laid over the turf for the tournament.

Heat stress is a shade Wet-Bulb Globe Temperature proxy from the venue's climatology mean temperature and humidity; FIFA mandates cooling breaks at WBGT 32 °C. Evening kickoff (local time). These are long-window averages, not a match-day forecast, and they are not inputs to the forecast.

Top scorers · P(scores in this match)

Belgium
New Zealand

Per-player scoring rate from Model #5 (`p_score_per_match`). Reflects each player's npxG/90, expected minutes, team xG share, and the average opposing-team defence. See /docs/methodology/.

Recent match form

Last match player ratings

Belgium

vs Senegal · avg 8.0

8
Thibaut CourtoisGK
ATK
DEF
PAS
8
Romelu LukakuST
ATK
DEF
PAS
8
Dodi LukébakioRW
ATK
DEF
PAS

New Zealand

vs Egypt · avg

Worked well: Their ability to respond to deficits and score from headers highlighted their determination and effectiveness in aerial duels.

Struggled: Despite their comeback, they struggled to contain Egypt's attacking threats, ultimately conceding four goals.

Player scores from official highlight analysis of each team's most recent match. Observational, not a model input. Methodology →

Video analysis: player performance

Per-player ratings and event breakdowns from official highlights analysis. Tap a player to see their full match timeline.

Belgium
9
Leandro Trossard6'–44'

Trossard was clinical in front of goal, scoring two crucial goals that set Belgium on their way to victory.

2goals1shots1on target

Match timeline

6'Belgium attack, shot by Trossard is saved by the goalkeeper, ball rolls near the goal line.
30'Trossard scores for Belgium after a scramble in the box. New Zealand 0-1 Belgium.
44'Trossard scores his second goal for Belgium with a close-range finish after receiving a pass from De Bruyne. New Zealand 0-2 Belgium.
9
Kevin De Bruyne44'–44'

De Bruyne orchestrated Belgium's attack with a goal and a key assist, demonstrating his exceptional vision and passing.

Match timeline

44'Trossard scores his second goal for Belgium with a close-range finish after receiving a pass from De Bruyne. New Zealand 0-2 Belgium.
9
Romelu Lukaku

Lukaku made an immediate and decisive impact, scoring two goals with clinical finishing to further extend Belgium's lead.

7
Thibaut Courtois5'–57'

Courtois made vital saves and confidently handled aerial threats, contributing to Belgium's defensive solidity despite the scoreline.

3saves

Match timeline

5'Belgium goalkeeper Courtois makes a diving save from a close-range shot by Senegal.
54'Belgium goalkeeper Courtois makes a diving save from a long-range shot.
57'Belgium goalkeeper Courtois makes a save from a shot inside the box.
6
Maxim De Cuyper

De Cuyper contributed to the attack with a strong shot on goal, showing offensive intent.

New Zealand
7
Elijah Just

Just provided New Zealand's only goal, showing good positioning to capitalize on a corner.

5
Chris Wood

Wood had a shot blocked, but otherwise struggled to make a significant impact in a difficult match for his team.

Match observations

  • The match began with early pressure from Belgium, almost resulting in a goal that was disallowed by goal-line technology.
  • Belgium quickly established dominance, scoring two goals through Trossard, showcasing their attacking prowess.
  • New Zealand managed to pull one goal back from a corner, but Belgium responded swiftly with two more goals from Lukaku.

Under the hood

Model-by-model comparison

Belgium vs New Zealand

Moderate (9.2%)
ModelWeightHomeDrawAway
EloRating-based strength estimate32%
74.8%
22.0%
3.2%
Dixon-ColesGoal-process model with low-score correction63%
83.0%
12.9%
4.1%
Hierarchical PoissonBayesian model with confederation pooling6%
82.4%
12.8%
4.8%
Bayesian stackingLearned-weight combination
90.9%
9.1%
0.0%
Ensemble (published)Uniform average + isotonic calibration
82.9%
15.7%
1.4%
Home spread: 8.2%
Draw spread: 9.2%
Away spread: 1.6%
How each model works
Elo
Each team carries a single strength rating updated after every match by a margin-aware K-factor. Match probabilities come from the logistic function of the rating gap. Elo is fast-adapting but coarse — it sees only who won and by how much, not how the goals were scored.
Dixon-Coles
A Poisson regression on team-level attack and defence parameters, fitted via maximum likelihood with an exponential time-decay weighting. The Dixon-Coles correction adjusts the four low-score cells (0-0, 1-0, 0-1, 1-1) where independent Poisson underestimates dependence. Produces full scoreline distributions, not just H/D/A.
Hierarchical Poisson
A Bayesian Poisson model fitted via MCMC (PyMC) with hierarchical priors that pool attack and defence parameters within confederations. Shrinks small-sample teams toward their confederation mean — helpful for nations with few recent competitive fixtures. Slower to fit but better-calibrated on the tails.
Bayesian stacking
Optimises simplex weights (w_elo, w_dc, w_hp) to maximise the leave-one-out log-score across a walk-forward backtest (Yao et al. 2018). The result is a weighted average of the three component models' probabilities, then isotonic-calibrated. Adds no extra features — just learns which component to trust more from historical accuracy.
Ensemble (published)
Equal-weight average of all three component models, followed by per-class isotonic regression calibration fitted on 24 months of walk-forward out-of-fold predictions. This is the probability published on the site. The uniform mean is deliberately simple — it avoids overfitting to the stacking weights' training window.

Three independent component models feed two combination strategies. The uniform ensemble is the published probability; Bayesian stacking uses learned weights. Amber bars flag >5pp divergence from the published number. Full methodology

Probability decomposition (transparency surface)

  • Baseline ensemble — P(Belgium win)70.1%
  • + Lineup contribution0.0pp
  • + Style-matchup contribution+0.1pp
  • Published P(Belgium win)70.2%
Belgium
70.2%
Draw
20.4%
New Zealand
9.4%

Decomposition of the published P(Belgium win) into the calibrated- baseline plus contributions from the §2.3 expected-XI lineup delta and the §2.7 style-matchup interaction. The §2.7 roadmap is explicit that style effects are second-order to team strength — single-digit-percentage P(win) shifts on extreme style matchups, near-zero on balanced ones. We surface the decomposition for transparency even when the contributions are small; the baseline carries the prediction. Methodology: /docs/methodology.

Latest news & match context

Match conditions
Stage:
Group G · Matchday 3
Date:
26 Jun
Availability

Belgium

Belgium come in at close to full strength.

New Zealand

New Zealand come in at close to full strength.

What it means

Belgium and New Zealand both come in at close to full strength, so the forecast rests on baseline team strength rather than late team-news swings.

The model's style-matchup analysis nudges the forecast −0.1pp toward a draw, versus the baseline team-strength prior.

Availability from the predicted squads and injury feed; forecast adjustments from the model's own decomposition. See /docs/methodology/.

Standard Pass

This match is a free preview

You're seeing the model's full forecast for this fixture for free. Unlock the same depth: probabilities, expected goals, scoreline distributions, and per-player scoring, for all 104 matches with a Standard Pass, valid through the tournament.

Get the Pass, $15

Every forecast graded against the real result, scored on 987 matches since 2014. See the scorecard.

24h money-back, no questions asked·No subscription, no auto-renewal·Access through 31 Dec 2026. See refund policy.