We Asked 7 AI Agents to Predict the 2026 World Cup: Here’s What They Said

The 2026 World Cup kicks off in days, which suggests half the planet is about to faux it might probably predict the longer term.

Everyone’s bought a take. Your group chat has one. Your fútbol-obsessed coworker has one. And this yr, so does the neatest software program ever constructed.

AI has, maybe not so quietly, was our go-to oracle. We let these fashions write our emails, debug our code, plan our holidays and diagnose the three a.m. rash—so after all we additionally ask them who lifts the trophy. They will crunch the squads, weigh the shape, and hand you a champion with a certainty the remainder of us can solely pretend.

I’ve pulled this occasion trick earlier than—an AI dream team on my March Insanity bracket (which sucked), a selfmade HorseGPT on the Kentucky Derby (which was really type of good). Equal components genuinely helpful and deeply humbling.

So with the largest event on Earth nearly right here, we ran it again—greater than ever.

We created Hermes brokers, configured them with entry to statistics websites (the free ones, not those that value one kidney per 30 days to make use of), set them up with customized expertise and handed seven of the world’s most superior AI fashions the identical job: forecast the 2026 World Cup, champion all the way down to the also-rans, and present their work. Every bought the actual draw—48 groups, 12 teams, the complete bracket—and complete freedom on how you can crack it.

Then we sat again and allow them to argue.

4 picked Spain. Three picked Argentina. And the road between them turned out to be much less about soccer than about which numbers every machine selected to belief.

Here is what all seven mentioned—choose your facet.

Opus 4.8 Max — The Meteorologist

Decide: Spain. 20% / Dixon-Coles Poisson + Monte-Carlo bracket · remaining: Spain def. France

Anthropic’s Opus 4.8 Max handled the World Cup like a physics downside. It took every group’s Elo ranking, turned the gaps into anticipated objectives with a Dixon-Coles mannequin—the type bookmakers really use—and simulated the bracket hundreds of instances. Spain got here out the champion at 20%, previous France within the remaining, with Portugal and England crushed within the semis.

Its actual obsession, although, was every thing taking place off the ball. Opus was the one mannequin within the area to cost within the situations a spreadsheet often ignores—warmth, skinny mountain air, and continent-sized journey.

It flagged that roughly 5 matches fall in warmth extreme sufficient that gamers’ performances could also be affected, and that visiting groups climbing to 2,200 meters on the Azteca are inclined to wilt within the remaining 20 minutes. It handled all of it as a quiet tax on the fitter, deeper European sides.

Then it did the coldest factor on the board and gutted Brazil. With Rodrygo’s knee gone, Estêvão damage and a 34-year-old Neymar dragged again for one final dance, Opus lower the five-time champions’ odds to eight%—half what the Argentina-leaning fashions gave them.

Its sharpest name was the quarterfinal it billed as “the actual remaining, a spherical early”: Spain over Argentina, a 39-year-old Messi pressed into the turf. For the Golden Boot it took Mbappé and barely blinked.

GPT 5.5 — The Cautious Scout

Decide Spain 15–18% / 5 weighted buckets, no simulation · remaining: Spain 2-1 France

OpenAI’s GPT 5.5 did not belief a single huge quantity, so it constructed a scorecard as an alternative. Each group bought graded throughout 5 weighted columns—squad high quality counted most at 35%, then tactical management, ending, availability and the kindness of the draw. It stored the weights intentionally blunt to keep away from kidding itself that soccer is extra predictable than it’s.

Spain got here out on high, however solely at 15–18% odds of profitable, and it could not faux to be extra exact than that. “Ranges quite than pretend precision,” it wrote, projecting Spain to beat France 2-1 in a remaining it anticipated to be determined by a single aim or additional time.

What made it the scout was the legwork. GPT 5.5 cross-checked itself towards Opta’s 25,000-run supercomputer—which landed in practically the identical spot, Spain first at 16.1%—then went studying the Spanish sports activities press for issues a mannequin cannot see.

It surfaced a training-ground scare within the Spain camp, a stray Gavi problem that left Rodri on the ground, and the cautious reintegration of Yamal and Nico Williams after muscle bother. None of it moved the choose, nevertheless it lowered the boldness—precisely what a very good scout does.

Its semifinal 4 had been Spain, France, Brazil, and Argentina, and it was blunt about England: loaded, genuinely harmful, and more than likely stopped by France earlier than the final 4.

DeepSeek v4 Professional — The Maximalist

Decide Argentina 18% / Qualitative tiers · remaining: Argentina vs France

DeepSeek v4 Professional answered a easy query with a 5,000-word epic. It did not simply identify winners; it constructed your entire Spherical of 32, annotated all 48 squads, and weighed journey all the way down to the 4,500 kilometers between Vancouver and Miami. If the others wrote previews, DeepSeek wrote the working handbook.

All that element led someplace contrarian: Argentina, at a tournament-best 18%, edging out France for the trophy in a Messi-versus-Mbappé remaining in Miami-which is a hallucination: The ultimate will happen at MetLife Stadium in New Jersey.

The case was old school—the champions have the calmest backbone, the softest group, and a coach who has received tournaments understanding precisely how you can ration a 39-year-old Messi.

Then it wager your entire forecast on one calf muscle. DeepSeek determined the title hinged on France’s goalkeeper Mike Maignan and his March damage: “If Maignan performs, France are co-favorites; if not, the hole widens,” it argued.

The wrinkle is that DeepSeek was studying an previous map. It nonetheless had Gareth Southgate within the England dugout and Dorival Júnior managing Brazil—each gone in 2024—and leaned on outdated rankings all through.

It was essentially the most thorough analyst within the constructing, working from a barely out-of-date file. Spectacular and faintly haunted, like a detective who cracks the case utilizing final yr’s cellphone e book.

Stepfun 3.7 — The True Believer

Decide Spain 33% / Pure-Elo Monte Carlo, 50,000 sims · remaining: Spain vs Argentina

No mannequin believed more durable. Stepfun 3.7 ran 50,000 simulated tournaments and topped Spain at a wild 33%—practically double the conviction of anybody else, with Argentina a distant second at 15%.

However one of the best factor Stepfun did was fail in public. Its first try was a fancier mannequin that attempted to invent expected-goal numbers for nationwide groups, and it produced nonsense—Mexico, South Africa, and South Korea got here out as top-three favorites to win the World Cup.

Reasonably than bury that, Stepfun defined the entire misadventure, labored out that the made-up stats had flattened the actual gulf between good groups and nice ones, then scrapped it and rebuilt on uncooked Elo alone. The brand new model was less complicated, blunter, and much more wise.

The trade-off is that pure Elo is blind to something human. Stepfun’s Spain would not know Lamine Yamal has a hamstring damage, would not assess warmth or journey, and treats a penalty shootout as a coin weighted by ranking. It is a fantastically sincere machine that has by no means as soon as watched a recreation of soccer.

Its bracket marched to the apparent locations—Spain previous Argentina in a single semi, the hosts and Brazil gone earlier—and planted its flag: Spain, comfortably, a 3rd of the time. Probably the most assured choose on the board, and essentially the most upfront about why you should not utterly belief it.

By the best way, the agent mixing Spanish and English in the identical reply was a conduct confirmed to be fairly exhausting to steer away from with this mannequin. This agent was a polyglot and switched between English, Spanish and Portuguese all through the entire session. That occurs when your agent learns you communicate no matter language is less complicated at any given second.

Nemotron 3 Extremely — The Double-Checker

Decide Spain 18–22% / Bivariate Poisson + a subjective twin · remaining: Spain vs Argentina

Nvidia’s Nemotron 3 Extremely did not belief itself, so it ran the event twice. The primary go was a chilly simulation, a bivariate-Poisson mannequin grinding via 5,000 brackets. The second threw the mathematics out and scored groups by hand—squad, ways, type, the supervisor, even “mystique”—to see whether or not a human-style learn would disagree.

It did not. Each variations topped Spain, at 18% and 22% odds, about as near a second opinion as one mannequin may give you.

Nemotron additionally did essentially the most homework on the precise soccer. It arrived with formations, urgent depth and expected-goal charges for group after group, in two languages, studying much less like a forecast than a coach’s file.

That depth produced the spiciest take of the experiment. Nemotron had Türkiye—not the host United States—profitable the wide-open Group D, with the Individuals ending lifeless final whereas everybody else waved them via; it additionally rated Ecuador’s miserly protection a notch above Germany.

When the mud cleared it lined up the heavyweight semis half the planet expects, Spain–France and Argentina–Brazil, and despatched Spain via to carry it. A mannequin that argued with itself, did additional studying, and nonetheless landed on the favourite is attempting to inform you one thing.

MiniMax 2.7 — The Self-Auditor

Decide Argentina 18% / Qualitative, self-audited · remaining: Argentina vs France, no scoreline

MiniMax 2.7 picked Argentina at 18% odds, a hair forward of France—after which spent its closing pages grading its personal work. Most fashions disguise their uncertainty; MiniMax printed a working checklist of corrections, brazenly strolling again issues it had gotten improper earlier in the exact same report.

The receipts are a delight. It caught itself repeating a bogus stat about South American champions, mounted Uruguay’s teaching state of affairs, corrected Kai Havertz’s place to match his precise membership position, and slapped an “unconfirmed” on each Haaland’s health and Ronaldo’s choice quite than wave them via.

It policed its personal hype, too. MiniMax deleted a tempting Messi-versus-Ronaldo semifinal as soon as it realized the pairing was unattainable—the 2 are in reverse halves and may solely meet within the remaining—and stripped out the invented scorelines different fashions fortunately printed.

Then, on the decisive second, it merely declined to guess. Argentina towards France, MiniMax wrote, is “a real 50/50,” and it could not manufacture a winner it did not have.

In a area of supremely assured robots, the restraint landed. MiniMax was the one which stored saying, in writing, right here is strictly what I do not know—which is one way or the other extra reliable than a tidy prediction.

Qwen 3.5 — The Contrarian With Receipts

Decide Argentina 22% / Analysis-only, no sims · remaining: Argentina 2-1 Spain

Qwen 3.5—a 397-billion-parameter mannequin—was essentially the most evidence-obsessed of the lot and, one way or the other, the largest insurgent. It refused to run simulations in any respect, sorting each assertion into “verified information,” “estimates” and “forecasts,” and stamping its total confidence, in its personal capital letters, as LOW.

Then it went rogue. Qwen had Argentina beating Spain 2-1, with Spain stranded down in fifth at simply 10%—the one mannequin that did not even put La Roja on the rostrum.

The explanation was the ruler it grabbed. The Spain camp used the stay soccer Elo that ranks Spain first on the planet; Qwen reached for a club-based ranking that slotted Argentina, Brazil, France, and England all forward of it. This switches views, all of the sudden producing a distinct favourite.

Its case for Argentina was all texture—champions’ muscle reminiscence, Messi chasing an ideal ending, and one stat it leaned on exhausting: on the final World Cup, groups that noticed much less of the ball received 38% of knockout video games. Organized and ruthless beats fairly and possession-heavy, it argued.

There was a worth for all that diligence. Probably the most fact-proud mannequin additionally fumbled the fundamentals, sliding Scotland into the improper group and double-booking tiny Curaçao into two of them.

The place they really agree

Step again and the seven AI fashions combat much less about their predictions than it appears to be like. Each single mannequin put Spain, Argentina, and France in its high tier, named nearly similar group winners—Brazil, England, Portugal, Germany, Belgium—and flagged the identical wildcards: Haaland’s health, Messi’s age at 39, and a Group D no one may name.

The fault line was the information, not the soccer. The 4 that trusted stay soccer Elo, the place Spain sits clearly first, picked Spain. The three that leaned on FIFA’s rating, a distinct Elo supply, or uncooked 2022 pedigree, drifted to Argentina. Feed a mannequin a distinct primary, and it arms you a distinct champion.

What the people with cash on the road assume

The group sides with the plurality. On Myriad, the prediction market run by Decrypt‘s father or mother firm Dastan, Spain is the outright favourite at 19%, with France proper behind at 17%, as of Sunday.

After that, the people get stingier with Argentina than the bots do. Bettors worth the defending champions at simply 10% odds of profitable—degree with Brazil, behind England and Portugal at 12%, and fewer than half the 22% Qwen handed them.

For what it’s price, predictors on Myriad are equally undecided on the Group D winner, with the percentages break up on Turkey and the US, even at 45%.

You may view the stay odds on Myriad for each single match of the World Cup here.

So who wins?

None of this can be a crystal ball, and all seven AI fashions mentioned so out loud. The most effective single-match soccer fashions are proper barely greater than half the time, which is why even Stepfun’s bullish 33% nonetheless means Spain falls quick two instances out of three.

The format solely widens the percentages: 48 groups, 104 matches, three international locations, actual warmth and actual altitude. Italy, four-time champions, did not even qualify.

Apart from the standard hallucinations when fashions need to be inventive of their analyses, there might also be some affirmation bias. Bear in mind it was a human who set these brokers up. The immediate, the interplay, the configuration, the concepts for analysis and sources, all had been influenced by the agent’s architect. Possibly, if all these components level to Spain, all brokers will attain an analogous conclusion. That mentioned, leaving a mannequin within the wild and easily asking it “Who will win the World Cup” just isn’t going to do a greater job.

So take the seven robots the best way I take my very own bracket—a good way to start out a combat on the bar, not a motive to remortgage the home and wager all of it.

4 machines say Spain. Three say Argentina. The gorgeous recreation, which has by no means as soon as relied on an AI-written report, will do precisely because it pleases.