WC 2026 · Forecasting Oxford Football Forecasting
🇨🇴 Colombia CONMEBOL Elo 1,982 · world 6th
62 / 26 / 12 win · draw · win most likely 1–0
🇨🇩 Congo DR CAF Elo 1,661
Group
K
Date
Wednesday 24 June 2026
Kick-off
02:00 UTC
Venue
Guadalajara Stadium, Guadalajara

Fig. V7 Ensemble · Group K

Colombia v Congo DR — scoreline probabilities

0 Colombia 0–0 Congo DR · 12.70% 13 Colombia 0–1 Congo DR · 5.76% 5.8 Colombia 0–2 Congo DR · 1.83% 1.8 Colombia 0–3 Congo DR · 0.34% Colombia 0–4 Congo DR · 0.05% Colombia 0–5 Congo DR · 0.01% Colombia 0–6 Congo DR · 0.00% Colombia 0–7 Congo DR · 0.00% 21% 1 Colombia 1–0 Congo DR · 17.87% (most likely) 18 Colombia 1–1 Congo DR · 11.21% 11 Colombia 1–2 Congo DR · 2.88% 2.9 Colombia 1–3 Congo DR · 0.53% 0.5 Colombia 1–4 Congo DR · 0.07% Colombia 1–5 Congo DR · 0.01% Colombia 1–6 Congo DR · 0.00% Colombia 1–7 Congo DR · 0.00% 33% 2 Colombia 2–0 Congo DR · 14.75% 15 Colombia 2–1 Congo DR · 8.18% 8.2 Colombia 2–2 Congo DR · 2.27% 2.3 Colombia 2–3 Congo DR · 0.42% Colombia 2–4 Congo DR · 0.06% Colombia 2–5 Congo DR · 0.01% Colombia 2–6 Congo DR · 0.00% Colombia 2–7 Congo DR · 0.00% 26% 3 Colombia 3–0 Congo DR · 7.75% 7.8 Colombia 3–1 Congo DR · 4.30% 4.3 Colombia 3–2 Congo DR · 1.19% 1.2 Colombia 3–3 Congo DR · 0.22% Colombia 3–4 Congo DR · 0.03% Colombia 3–5 Congo DR · 0.00% Colombia 3–6 Congo DR · 0.00% Colombia 3–7 Congo DR · 0.00% 13% 4 Colombia 4–0 Congo DR · 3.06% 3.1 Colombia 4–1 Congo DR · 1.70% 1.7 Colombia 4–2 Congo DR · 0.47% Colombia 4–3 Congo DR · 0.09% Colombia 4–4 Congo DR · 0.01% Colombia 4–5 Congo DR · 0.00% Colombia 4–6 Congo DR · 0.00% Colombia 4–7 Congo DR · 0.00% 5% 5 Colombia 5–0 Congo DR · 0.96% 1.0 Colombia 5–1 Congo DR · 0.53% 0.5 Colombia 5–2 Congo DR · 0.15% Colombia 5–3 Congo DR · 0.03% Colombia 5–4 Congo DR · 0.00% Colombia 5–5 Congo DR · 0.00% Colombia 5–6 Congo DR · 0.00% Colombia 5–7 Congo DR · 0.00% 2% 6 Colombia 6–0 Congo DR · 0.25% Colombia 6–1 Congo DR · 0.14% Colombia 6–2 Congo DR · 0.04% Colombia 6–3 Congo DR · 0.01% Colombia 6–4 Congo DR · 0.00% Colombia 6–5 Congo DR · 0.00% Colombia 6–6 Congo DR · 0.00% Colombia 6–7 Congo DR · 0.00% 0% 7 Colombia 7–0 Congo DR · 0.06% Colombia 7–1 Congo DR · 0.03% Colombia 7–2 Congo DR · 0.01% Colombia 7–3 Congo DR · 0.00% Colombia 7–4 Congo DR · 0.00% Colombia 7–5 Congo DR · 0.00% Colombia 7–6 Congo DR · 0.00% Colombia 7–7 Congo DR · 0.00% 0%

Cells show P(exact scoreline); the right column and bottom row are the marginal totals P(Colombia scores k) and P(Congo DR scores k). Grid runs 0–7 goals per side; the 8–10-goal tail holds 0.02% of the mass and is omitted from the cells (not from the totals).

The grid makes Colombia favourites at 61.6%, with a 26.4% draw. The single most-likely scoreline is 1–0 (17.9%), but no exact score clears 18% — the distribution is broad, as it should be.

Source · Oxford Football Forecasting model

Win · draw · loss

🇨🇴 Colombia 61.6% Draw 26.4% 🇨🇩 Congo DR 12%

Rounded values sum to exactly 100%.

Expected goals (λ)

🇨🇴Colombia 1.58
🇨🇩Congo DR 0.56

Poisson means feeding the grid; combined expected goals 2.13.

35.9% Over 2.5 goals P(3 or more goals in the match)
64.1% Under 2.5 goals complement of over-2.5
34.6% Both teams to score P(each side scores ≥ 1)
1–0 Most-likely scoreline modal exact score · 17.9%
Akron Guadalajara, Mexico
Heat index 30°C apparent temperature (June–July)
Max temperature 28°C June–July daily high
Humidity 71% relative humidity
Altitude 1,671m high-altitude venue

Source · Open-Meteo & venue records. Travel and time-zone exposure are per-team — see each side's dossier.

1,982 Elo rating 1,661
1.67 Recent NT form 2.20
€382M Squad value €184M
0.285 Squad form (global) 0.154
0.809 Fitness readiness 0.557
+0.47 Decoupling g −0.30

Colombia carry the Elo edge (321 points). On the decoupling axis, Colombia is the side whose squad is valued higher relative to its record.

How a single-match forecast is built

The pairing is scored by the ensemble — Dixon-Coles bivariate-Poisson, the Bayesian hierarchical model and the global LightGBM-Poisson, log-pooled — yielding the 11×11 scoreline grid above. Win/draw/loss, expected goals (λ), over-2.5 and both-teams-to-score are all marginals of that one grid, so they are mutually consistent by construction. The strength inputs shown here feed the models; the forecast is their pooled output, not a manual weighting of these rows. The model matches the market out-of-sample (RPS 0.1891 vs 0.1905); it does not significantly beat it at n = 3. The ensemble, in full →