World Cup forecasts, with the receipts.
Every match here gets two forecasts. A statistical model — the same method for every team, fit on 47,000+ international results — rates each side’s attack and defense and simulates the whole tournament thousands of times. Then an AI agent takes one fixture at a time: the model’s odds and how sure they are, the betting-market price, and the things the numbers can’t see — injuries, line-ups, weather, altitude, the week’s news — and writes a reasoned call.
Most of the time it agrees with the model; sometimes it nudges it; it always shows its work. Once a match is played we score the call against the model — not because a well-calibrated model is easy to beat, but to see where reading the context actually helps, and to say so plainly.
Portugal WDWWW, +0.52 pts/match vs expectation vs avg opponent rank #45; DR Congo LWWDL, -0.17 pts/match vs avg opponent rank #68. Portugal is overperforming against stronger opposition.
Calibrated on 47,000+ international matches · scored against real results as they come in · the agent weighs in on each fixture as kickoff nears.
How the forecast agent works
A statistical model rates every team’s attack and defense from 47,000+ international results, weighting recent matches most. It then plays the tournament out thousands of times to get each side’s odds — to win its group, survive the knockouts, lift the trophy. One disciplined method for everyone, no opinions in it.
For one fixture the agent gets a single brief: the model’s odds and how sure they are, the betting-market price, and what the numbers structurally miss — injuries, line-ups, suspensions, and the match-day conditions that may swing a game: altitude, heat, a roof that closes. It weighs them and writes a reasoned call — usually confirming the model, sometimes nudging it, always citing what tipped it.
Once the match is played we score the call — the W/D/L result and how close the scoreline came. Soccer is hard to call — low-scoring, and national sides barely play together — so we keep expectations honest and show every call, win or lose. The method →
Every one of the tournament’s 104 fixtures gets both reads — the W/D/L odds (a win, draw or loss for the home side) and a most-likely scoreline — laid out across the group stage and the knockout bracket. It’s a small demonstration of a larger idea: an agent that blends the numbers with the context a model misses and reasons out loud — a sounding board, not an oracle.
The agent
A few of the latest calls. Each card carries the model’s number, the agent’s adjustment and the one fact behind it; the full agent surface has them all, with sources and grades. Most calls sit close to the baseline — the agent’s sharpest move so far is Portugal +13.8 pp.
Algeria DWWLW (+0.79 pts/match vs expectation vs avg rank #34); Austria WWWWL (+0.47 vs avg rank #45). Both over-perform, but Algeria's overperformance is larger against tougher opposition.
Jordan DLLLL (-0.54 pts/match vs expectation, opponents avg rank #23); Argentina WWWWW (+0.56 pts/match, opponents avg rank #56). Jordan underperforming against strong opposition; Argentina overperforming against weaker opposition.
Colombia are LWWWW, over-performing by +0.54 pts/match vs expectation against average rank #53 opponents; Portugal are WWWDW, in line with expectations (+0.15) vs average rank #43 opponents.
The forecast, in brief
Full 48-team table →Straight out of the model — attack and defense ratings, run through thousands of simulated tournaments. The top of the field, and the baseline the agent reasons from. Each market’s de-vigged champion price sits beside the model’s, never blended. Top 8 ≈ 70% of the title mass — an unusually flat field.
| # | Team | Champion | Final | Semi | Polymarket | Kalshi |
|---|---|---|---|---|---|---|
| 01 | Spain | 14.2% | 22.8% | 34.8% | 18.7% | 18.6% |
| 02 | Brazil | 12.9% | 20.6% | 33.6% | 6.6% | 6.8% |
| 03 | Argentina | 11.8% | 19.3% | 31.5% | 20.0% | 18.8% |
| 04 | England | 9.3% | 15.9% | 26.8% | 15.8% | 15.5% |
| 05 | France | 6.5% | 12.8% | 23.4% | 32.1% | 33.1% |
| 06 | Portugal | 6.5% | 12.4% | 22.6% | 5.9% | 6.2% |
| 07 | Germany | 5.0% | 10.5% | 20.9% | 3.9% | 3.5% |
| 08 | Colombia | 4.6% | 9.2% | 18.0% | 3.4% | 3.3% |
What changed
Champion odds over the last dayFind your way around
Every fixture by date — the model’s W/D/L odds, the likely score, and the agent’s call, group stage through the final.
Every call the agent has made, with the reasoning, the sources it pulled, and how each one was graded.
Champion and stage odds for all 48 teams, with the market prices beside them.
Where the model disagrees with Polymarket and Kalshi — published ahead, scored later.
When the model says 60%, does it happen 60% of the time? The public record.
How the model is built and scored, the sources, and why soccer is hard to call.