xAI’s new Grok 4 mannequin picked the Dodgers to win this yr’s World Sequence in a stay demo.
We requested different prime AI fashions to make their very own projections and received blended outcomes.
You may as well construct your personal particular prompts and GPTs for the duty, as detailed beneath.
Among the many demos Elon Musk confirmed off throughout Grok 4’s launch on July 9 was a banger asking the AI to foretell which workforce will win Main League Baseball’s World Sequence later this yr.
After 4.5 minutes of number-crunching that analyzed information from Polymarket, the Ethereum-based prediction markets platform, and utilizing what xAI calls its “Heavy” reasoning capabilities, Grok 4 delivered its verdict: The Los Angeles Dodgers are the most certainly workforce to win the 2025 World Sequence. Grok gave L.A. a 21.6% likelihood to win all of it—larger than some other workforce, however nonetheless famous they is perhaps overpriced.
Grok’s predictions are definitely consistent with different main platforms, together with ESPN BET, which exhibits the Dodgers sitting at +225 because the MLB season approaches the All-Star break. The Detroit Tigers (+750), who’re operating away with the AL Central, have emerged as a darkish horse contender with baseball’s greatest file at 59-35.
Merchants on X are giddy concerning the potential of getting a private Grokstradamus and calling the outcomes an “infinite cash glitch.”
However we wished to know: Did the opposite main AI fashions agree with Grok?
Seems, not solely.
What different AIs assume
ChatGPT’s o3 mannequin gave the Dodgers a 26% likelihood whereas flagging them as overpriced. The mannequin recognized Detroit as providing the perfect worth with a 16% win likelihood in opposition to market odds implying simply 12.5%. Its reasoning centered on Tigers ace Tarik Skubal’s dominance and the workforce’s league-best pitching employees.
DeepSeek doubled down on Los Angeles with a 23% likelihood, however famous the Dodgers is perhaps using an excessive amount of optimistic sentiment. Regardless of favoring LA to win, the mannequin mentioned it will relatively wager on the Phillies as a result of the risk-to-reward ratio was extra compelling.
Since we’re poor and our paymasters had been unlikely to approve Grok 4 Heavy’s $300 subscription for only one query, we requested the lighter Grok 4 model accessible by way of the $30 tier. Curiously, it gave the Tigers a razor-thin edge over the Dodgers—lower than one share level separated their odds.
All three fashions flagged related elements: Detroit’s elite pitching rotation, the Dodgers’ harm issues, and historic patterns suggesting the market overvalues defending champions.
It is all within the immediate
Whereas Grok 4’s “Heavy” reasoning is spectacular, you don’t want a $300/month plan to get strong predictions. With sensible prompting, even primary fashions can ship sharp insights. We discovered that profitable prompts want at the least these three principal parts:
First, role-play. Inform the mannequin who it must be and the way it ought to act. Attempt one thing like: “You’re an knowledgeable Prediction Market Analyst with deep information of Bayesian forecasting and threat administration.”
Second, the methodology: Inform the mannequin what you need and what steps it ought to observe so as to succeed. Ask the mannequin to collect present betting odds from a number of sources, examine them in opposition to analytical projections, and establish worth bets. Fashions carry out higher once they can examine market consensus in opposition to their very own calculations.
That is what immediate engineers name Chain-of-Thought—if the mannequin is aware of precisely what to do, it supplies higher outcomes. Do not know the best way to information it? Ask the mannequin individually for the steps wanted to finish your activity.
Third, level towards analytical sources. Mentioning Baseball-Reference simulations or FanGraphs projections helps floor predictions in established frameworks, relatively than pure hypothesis.
For these excited by making an attempt this themselves, we constructed a customized GPT that replicates what xAI demonstrated with Grok 4. It was only a enjoyable experiment, but it surely gathers odds, analyzes workforce efficiency, and identifies potential betting worth by pure dialog.
We additionally tossed our prediction market immediate on GitHub if you wish to experiment with your personal chatbot.
Use at your personal threat, naturally. We’re not monetary advisors, and neither are these AIs. In case you lose, do not blame us—but when it helps you win large, then we can’t say no to a beer.
Usually Clever E-newsletter
A weekly AI journey narrated by Gen, a generative AI mannequin.
