World Cup 2026 — Validation
Every played match: our pre-match forecast vs. what actually happened. The receipts. 🧾
58.3%
Outcome accuracy
56 / 96 results called
Market 69.8%
6.2%
Exact scoreline
6 / 96 spot‑on
0.191
Avg. RPS (lower better)
coin‑flip baseline 0.243
Market 0.152
21.5%
Skill vs. coin‑flip
RPS improvement over uniform
Market = de-vigged bookmaker consensus over 96 matches with odds. SFMMO trails the closing market by 25.7% on RPS.
Outcome accuracy — share of matches where our most-likely result (1 / X / 2) was right.
RPS (ranked probability score) grades the whole probability forecast — it rewards being
confident and right, and is the standard metric for football results (lower is better, 0 = perfect).
Skill is how far the model beats a no-information coin-flip forecast.
All numbers are the SFMMO's pre-match probabilities, scored against the final result.
Wait — how can 58.3% accuracy still beat a coin-flip on RPS?
Because accuracy and RPS measure different things, on different scales — they're not in competition.
- Accuracy only asks: was our single top pick right? It's blind to the probabilities, and a model almost never makes draw its top pick — so a draw-heavy round drags it down even when the forecast was good.
- RPS grades the whole probability spread (e.g. 55 / 25 / 20) against a uniform “coin-flip” (33 / 33 / 33). The coin-flip never commits, so it's never punished hard — which makes it a surprisingly tough baseline, and means a few % of skill is a genuine edge.
Our committed forecast cuts both ways (lower RPS = better):
| Match | Our forecast | Result | Our RPS | Coin-flip RPS |
|---|---|---|---|---|
| Favourite delivers | 55 / 25 / 20 | home win | 0.12 ✓ | 0.28 |
| We back home, it's a draw | 55 / 25 / 20 | draw | 0.17 | 0.11 ✓ |
When a favourite wins we crush the baseline; on a draw, the hedging coin-flip actually beats us. Matchday 1 had 9 draws in 24 games, so the wins and losses partly cancel — the net edge is the “skill” figure above. A few % over uniform is roughly what bookmakers manage, so it's a real, healthy edge.
Knockout rounds can't end level — scores include extra time and penalty shootouts (a 3–4 may be a shootout result), and each match is graded on that final outcome.
Matchday 1
| Match | Forecast (1 / X / 2) | Our call | Predicted | Actual | |
|---|---|---|---|---|---|
| 52.0 / 27.0 / 21.0 | Mexico | 1–0 | 2–0 | ✓ | |
| 35.7 / 27.9 / 36.4 | Czechia | 1–1 | 2–1 | ✗ | |
| 35.2 / 24.5 / 40.3 | Bosnia & Herzegovina | 1–1 | 1–1 | ✗ | |
| 31.7 / 29.2 / 39.0 | Paraguay | 0–1 | 4–1 | ✗ | |
| 12.9 / 18.6 / 68.5 | Switzerland | 0–2 | 1–1 | ✗ | |
| 38.6 / 24.7 / 36.6 | Netherlands | 1–1 | 2–2 | ✗ | |
| 45.1 / 28.7 / 26.2 | Brazil | 1–0 | 1–1 | ✗ | |
| 25.1 / 25.5 / 49.4 | Scotland | 0–1 | 0–1 | ✓ ⚛ | |
| 37.8 / 23.2 / 38.9 | Türkiye | 1–1 | 2–0 | ✗ | |
| 65.0 / 19.7 / 15.3 | Germany | 2–0 | 7–1 | ✓ | |
| 18.6 / 25.4 / 56.1 | Ecuador | 0–1 | 1–0 | ✗ | |
| 48.2 / 26.2 / 25.7 | Sweden | 1–0 | 5–1 | ✓ | |
| 79.9 / 12.4 / 7.2 | Spain | 2–0 | 0–0 | ✗ | |
| 88.2 / 6.9 / 2.9 | Belgium | 3–0 | 1–1 | ✗ | |
| 22.8 / 27.0 / 50.2 | Uruguay | 0–1 | 1–1 | ✗ | |
| 53.9 / 27.7 / 18.4 | Iran | 1–0 | 2–2 | ✗ | |
| 70.1 / 19.0 / 10.9 | France | 2–0 | 3–1 | ✓ | |
| 26.2 / 26.8 / 46.9 | Norway | 0–1 | 1–4 | ✓ | |
| 74.4 / 15.0 / 10.3 | Argentina | 2–0 | 3–0 | ✓ | |
| 48.3 / 22.5 / 29.2 | Austria | 1–1 | 3–1 | ✓ | |
| 72.2 / 15.8 / 11.7 | Portugal | 2–0 | 1–1 | ✗ | |
| 35.2 / 27.5 / 37.3 | Croatia | 1–1 | 4–2 | ✗ | |
| 39.0 / 27.8 / 33.2 | Ghana | 1–1 | 1–0 | ✓ | |
| 28.1 / 26.1 / 45.7 | Colombia | 1–1 | 1–3 | ✓ |
Mexico
South Africa
South Korea
Czechia
Canada
Bosnia & Herzegovina
United States
Paraguay
Qatar
Switzerland
Netherlands
Japan
Brazil
Morocco
Haiti
Scotland
Australia
Türkiye
Germany
Curaçao
Ivory Coast
Ecuador
Sweden
Tunisia
Spain
Cape Verde
Belgium
Egypt
Saudi Arabia
Uruguay
Iran
New Zealand
France
Senegal
Iraq
Norway
Argentina
Algeria
Austria
Jordan
Portugal
DR Congo
England
Croatia
Ghana
Panama
Uzbekistan
ColombiaMatchday 2
| Match | Forecast (1 / X / 2) | Our call | Predicted | Actual | |
|---|---|---|---|---|---|
| 59.3 / 21.1 / 19.6 | Czechia | 1–0 | 1–1 | ✗ | |
| 57.6 / 20.3 / 22.0 | Switzerland | 2–1 | 4–1 | ✓ | |
| 48.0 / 24.0 / 28.0 | Canada | 1–1 | 6–0 | ✓ | |
| 36.4 / 31.0 / 32.5 | Mexico | 0–0 | 1–0 | ✓ | |
| 29.3 / 26.4 / 44.2 | Australia | 1–1 | 2–0 | ✗ | |
| 85.3 / 9.5 / 4.1 | Germany | 3–0 | 2–1 | ✓ | |
| 19.6 / 23.8 / 56.6 | Morocco | 0–1 | 0–1 | ✓ ⚛ | |
| 72.1 / 17.2 / 10.5 | Brazil | 2–0 | 3–0 | ✓ | |
| 49.6 / 23.0 / 27.4 | Türkiye | 1–1 | 0–1 | ✗ | |
| 48.5 / 22.4 / 29.0 | Netherlands | 1–1 | 5–1 | ✓ | |
| 52.4 / 25.1 / 22.4 | Ecuador | 1–0 | 0–0 | ✗ | |
| 15.4 / 23.3 / 61.3 | Japan | 0–1 | 0–4 | ✓ | |
| 64.1 / 19.9 / 15.9 | Spain | 2–0 | 4–0 | ✓ | |
| 64.7 / 22.0 / 13.3 | Belgium | 1–0 | 0–0 | ✗ | |
| 69.6 / 17.5 / 12.8 | Uruguay | 2–0 | 2–2 | ✗ | |
| 42.6 / 24.1 / 33.2 | New Zealand | 1–1 | 1–3 | ✗ | |
| 64.3 / 20.1 / 15.6 | Argentina | 2–0 | 2–0 | ✓ ⚛ | |
| 69.3 / 20.4 / 10.2 | France | 1–0 | 3–0 | ✓ | |
| 43.8 / 24.6 / 31.5 | Norway | 1–1 | 3–2 | ✓ | |
| 42.4 / 20.4 / 37.1 | Jordan | 1–1 | 1–2 | ✗ | |
| 68.6 / 17.4 / 13.9 | Portugal | 2–0 | 5–0 | ✓ | |
| 73.0 / 16.8 / 10.0 | England | 2–0 | 0–0 | ✗ | |
| 10.8 / 18.3 / 70.9 | Croatia | 0–2 | 0–1 | ✓ | |
| 45.8 / 24.3 / 29.9 | Colombia | 1–1 | 1–0 | ✓ |
Matchday 3
| Match | Forecast (1 / X / 2) | Our call | Predicted | Actual | |
|---|---|---|---|---|---|
| 48.7 / 26.3 / 24.9 | Switzerland | 1–0 | 2–1 | ✓ | |
| 58.7 / 19.8 / 21.5 | Bosnia & Herzegovina | 2–1 | 3–1 | ✓ | |
| 16.5 / 21.8 / 61.7 | Brazil | 0–1 | 0–3 | ✓ | |
| 57.8 / 23.7 / 18.5 | Morocco | 1–0 | 4–2 | ✓ | |
| 44.8 / 28.4 / 26.8 | Czechia | 1–0 | 0–3 | ✗ | |
| 24.1 / 24.4 / 51.5 | South Korea | 0–1 | 1–0 | ✗ | |
| 21.8 / 24.1 / 54.1 | Germany | 0–1 | 2–1 | ✗ | |
| 51.6 / 24.2 / 24.2 | Curaçao | 1–0 | 0–2 | ✗ | |
| 47.8 / 26.8 / 25.4 | Japan | 1–0 | 1–1 | ✗ | |
| 56.2 / 21.0 / 22.7 | Türkiye | 1–1 | 3–2 | ✓ | |
| 27.6 / 27.1 / 45.4 | Australia | 0–1 | 0–0 | ✗ | |
| 14.5 / 20.7 / 64.8 | France | 0–1 | 1–4 | ✓ | |
| 42.0 / 29.1 / 28.8 | Senegal | 1–0 | 5–0 | ✓ | |
| 13.5 / 18.4 / 68.0 | Netherlands | 0–2 | 1–3 | ✓ | |
| 26.9 / 23.5 / 49.6 | Spain | 1–1 | 0–1 | ✓ | |
| 25.9 / 25.8 / 48.3 | Saudi Arabia | 0–1 | 0–0 | ✗ | |
| 4.8 / 11.0 / 83.5 | Belgium | 0–2 | 1–5 | ✓ | |
| 13.2 / 20.0 / 66.8 | Iran | 0–1 | 1–1 | ✗ | |
| 13.4 / 21.2 / 65.5 | England | 0–1 | 0–2 | ✓ | |
| 71.7 / 16.8 / 11.3 | Croatia | 2–0 | 2–1 | ✓ | |
| 15.2 / 18.7 / 66.0 | Portugal | 0–2 | 0–0 | ✗ | |
| 42.0 / 25.0 / 33.1 | DR Congo | 1–1 | 3–1 | ✓ | |
| 15.9 / 20.3 / 63.7 | Argentina | 0–1 | 1–3 | ✓ | |
| 25.9 / 19.4 / 54.5 | Austria | 1–2 | 3–3 | ✗ |
Round of 32
| Match | Forecast (1 / X / 2) | Our call | Predicted | Actual | |
|---|---|---|---|---|---|
| 21.1 / 23.4 / 55.5 | Canada | 0–1 | 0–1 | ✓ ⚛ | |
| 46.7 / 27.5 / 25.9 | Brazil | 1–0 | 2–1 | ✓ | |
| 70.6 / 18.4 / 11.0 | Germany | 2–0 | 3–4 | ✗ | |
| 37.4 / 25.7 / 36.9 | Netherlands | 1–1 | 2–3 | ✗ | |
| 23.9 / 23.9 / 52.3 | Norway | 1–1 | 1–2 | ✓ | |
| 58.7 / 23.8 / 17.5 | France | 1–0 | 3–0 | ✓ | |
| 25.3 / 30.6 / 44.1 | Ecuador | 0–1 | 2–0 | ✗ | |
| 68.2 / 18.8 / 12.9 | England | 2–0 | 2–1 | ✓ | |
| 71.7 / 17.8 / 10.4 | Belgium | 2–0 | 3–2 | ✓ | |
| 31.6 / 24.5 / 44.0 | Bosnia & Herzegovina | 1–1 | 2–0 | ✗ | |
| 64.5 / 18.4 / 17.0 | Spain | 2–1 | 3–0 | ✓ | |
| 43.2 / 23.9 / 32.9 | Portugal | 1–1 | 2–1 | ✓ | |
| 65.7 / 18.1 / 16.1 | Switzerland | 2–1 | 2–0 | ✓ | |
| 64.3 / 19.0 / 16.6 | Australia | 2–1 | 2–4 | ✗ | |
| 67.7 / 19.2 / 13.0 | Argentina | 2–0 | 3–2 | ✓ | |
| 46.7 / 24.3 / 29.0 | Colombia | 1–1 | 1–0 | ✓ |
Round of 16
| Match | Forecast (1 / X / 2) | Our call | Predicted | Actual | |
|---|---|---|---|---|---|
| 29.6 / 29.2 / 41.2 | Morocco | 0–1 | 0–3 | ✓ | |
| 11.5 / 21.9 / 66.6 | France | 0–1 | 0–1 | ✓ ⚛ | |
| 64.0 / 20.8 / 15.1 | Brazil | 1–0 | 1–2 | ✗ | |
| 16.7 / 26.7 / 56.6 | England | 0–1 | 2–3 | ✓ | |
| 40.5 / 22.5 / 37.0 | Portugal | 1–1 | 0–1 | ✗ | |
| 7.9 / 16.0 / 76.0 | Belgium | 0–2 | 1–4 | ✓ | |
| 73.4 / 16.7 / 9.8 | Argentina | 2–0 | 3–2 | ✓ | |
| 45.0 / 25.9 / 29.2 | Switzerland | 1–1 | 4–3 | ✓ |
✓ = our most-likely result was correct · ⚛ = exact scoreline nailed · multiclass Brier score 0.553. Click any match for its full forecast breakdown.