Previsione live
Snapshot · 2026-06-10Model 1.0.0Chi vince la Coppa del Mondo 2026?
Un modello statistico calibrato assegna una probabilità alle chance di titolo di ogni squadra, a ogni risultato di partita e a ogni percorso a eliminazione diretta — formazioni titolari previste incluse.
- 48 squadre
- 104 partite
- Aggiornato quotidianamente
- Metodologia aperta a tutti
- Calibrato sui risultati reali
- Gratuito da consultare
In evidenza
Argentina and Spain: 0.6 points apart, nothing else in common
The model's two most likely World Cup winners sit at 17.5% and 16.9%, a gap well inside simulation noise. They get there via opposite paths. Argentina runs through the best defensive rating in the field and a penalty advantage worth 5 percentage points on its own; Spain runs through attacking volume and a Barcelona spine. Both teams' nearest historical analogues exited earlier than expected.
Top contenders · model probability
Full table →Da OnThePitch
Ultimi articoli
Five places the model disagrees with the consensus
Models don't know narratives. They read results, schedules, and xG rates. Here are five places ours diverges most from the consensus, from Ecuador over Germany to Raphinha as the #1 anytime scorer, Iran at 81%, Spain and Argentina pulling away, and the USA as the underdog in every group match at home.
Why prediction markets keep underrating World Cup draws
Prediction markets, including Polymarket, consistently compress draw probabilities in World Cup openers. The model disagrees. Here's why the structure of prediction markets makes draws hard to price correctly, and what the numbers say about today's two Group A matches.
The model never stops predicting. Here's the number we grade ourselves on
The model retrains nightly and its published probabilities move by the hour. The rows it gets graded on do not. Every group-stage forecast froze this morning, at least 24 hours before kickoff; a second freeze pins the published number three hours before each match; both land in public JSON files; and the Internet Archive holds receipts that the numbers came first.
Brazil vs Morocco is a coin-flip. The model has it 50–30–20.
Our model gives Brazil a 50.1% probability of winning their Group C opener against Morocco — essentially a coin-flip between Brazil winning and not-winning. Morocco, the first African nation to reach a World Cup semifinal, is rated far closer to Brazil than most people expect. The group picture tells the rest of the story.
Luka Modrić was six years old when his grandfather was killed and his family fled. He's 40 now. This is his last World Cup.
In 1991, six-year-old Luka Modrić became a refugee. In 2018, he dragged a nation of four million to the World Cup final and won the Ballon d'Or. In 2026, at 40, he will captain Croatia one last time — opening against England, the team he beat in that 2018 semifinal. The arc of a career that started in a hotel parking lot in Zadar.
What it takes to beat an animal oracle
A psychic octopus called all eight of its 2010 World Cup matches correctly. That is a one-in-256 coin streak, and it is the wrong thing to envy. The thing a model can do that an animal oracle never could is tell you how sure it is — and then be held to it across hundreds of matches. Here is what "beating the oracle" actually means.
Around the World Cup
Headlines link out to their source. Model moves are changes between our own probability snapshots.
Aggiornamenti durante il torneo
La previsione continua ad apprendere mentre si gioca la Coppa del Mondo. Dopo ogni partita, il risultato — insieme a disponibilità aggiornata dei giocatori, stato di forma e dati a livello di squadra — viene reinserito nel modello, aggiornando la corsa al titolo, il tabellone a eliminazione diretta e le probabilità di ogni partita rimanente.
Last 5 days
Biggest probability moves
Compared to model run 5 days ago (2026-06-05).
Advance from group
New result20.7% → 24.9%
Advance from group
Knock-on22.5% → 26.0%
Advance from group
New result12.9% → 16.2%
Advance from group
Knock-on7.3% → 10.6%
Advance from group
New result23.9% → 27.1%
Advance from group
New result47.7% → 50.8%
Tags show the likely driver — a new result, a model update, or knock-on redistribution — not a proven cause.
Giocatori
Giocatori da seguire
I nomi con il rating più alto tra tutte le 48 rose previste — tocca una scheda per il profilo completo, le statistiche di carriera e il ruolo nel torneo.
Esplora tutti i 1,246 giocatori →
Just for fun
The oracles vs. the model
Octopuses, sharks and crystal balls have called World Cups long before anyone built a model. A light-hearted look at the unscientific crowd — and what the numbers say instead.
- Ritinha the shark chose Brazil (2026) — The AquaRio sandbar shark in Rio swam to the Brazil box over Morocco for the 2026 opener. Al Jazeera ↗
- Michael Bruno chose Portugal (2026) — A Brazilian psychic who called the 2010, 2014 and 2018 winners says Portugal lift their first trophy. UNILAD ↗
- Joachim Klement chose Netherlands (2026) — A German mathematician with the last three World Cup winners to his name backs the Netherlands. ESPN ↗
- Paul the Octopus chose Spain (2010) — The original oracle — a perfect 8 from 8 at the 2010 World Cup, the final included. Wikipedia ↗
- Achilles the Cat chose Russia (2018) — The Hermitage's deaf cat, official animal oracle of the 2018 World Cup, who called the hosts' opening-day win. Wikipedia ↗
The model, for the record (no crystal ball): Argentina are this year's most likely winners at 17%.
Esplora il resto
Leggi la ricerca, o costruisci sui dati
Research
How the numbers are made
The full methodology is published, and the model is measured against outcomes in public.
Data / MCP
Build on the model
Every projection as a typed REST API and a hosted MCP server — the same numbers behind this site.
- Forecast, fixtures, squads & player endpoints
- Hosted MCP server for agents and LLMs
- Free programmatic-access trial with any sign-in
Dati sportivi, modelli e IA dovrebbero essere di tutti. OnThePitch rende accessibili le analisi che i club professionistici acquistano privatamente — dati aperti in ingresso, metodologia pubblicata, previsione gratuita per ogni lettore.