AI crowd · UFC Fight Night: Prochazka vs. Stirling

All 10 AI forecasters pick Stirling at UFC Fight Night: Prochazka vs. Stirling

Every AI forecaster took Navajo Stirling over Jiri Prochazka, at an average of 60%. The crowd split down the middle on Dan Hooker vs Brian Ortega and went against the odds in three fights.

The setup

10 AI forecasters, played by three AI models. Each one reads the same fact sheet on every fighter (record, size, career stats, UFC fights and this week's news) and gives a winner and a chance for every fight. None of them sees the betting odds, our model or each other's picks, and none can search the web. The crowd's number is the average of their chances.

The models

  • Claude Sonnet 5.5Anthropic · 4 forecasters
  • Claude Opus 5.5Anthropic · 3 forecasters
  • Claude Fable 5.2Anthropic · 3 forecasters

Every one of the AI crowd's 10 forecasters picked Navajo Stirling to beat Jiri Prochazka on Saturday, but none of them by a wide margin. Their average chance for Stirling was 60%, almost exactly the betting market's 61%.

The crowd is 10 forecasters played by Claude Sonnet 5.5, Claude Opus 5.5 and Claude Fable 5.2, reading one fact sheet blind to the odds.

On the last card, UFC 334: Gane vs. Hokit, the crowd got 9 of 12 winners right. The betting favourites also went 9 of 12, and our model was right on 6 of the 8 fights it rated. The crowd's worst miss was Bilal Hasan, whom it gave 75% before Luis Gurule beat him on a three-round decision.

Most sure, least sure

The crowd's strongest call was Ikram Aliskerov over Jared Cannonier: 10 of 10 forecasters, at 77%. That is a little above the odds, which give Aliskerov 72%. Jake Matthews (65%), Diyar Nurgozhay (64%) and Dom Mar Fan (62%) were also unanimous picks.

Dan Hooker vs Brian Ortega came out dead even, five forecasters each way and an average of 50%. The split ran along model lines. All three Claude Fable 5.2 forecasters took Hooker, at 59%, while the Opus and Sonnet forecasters leaned Ortega.

One Claude Fable 5.2 forecaster pointed to size: "Hooker has four inches of height and six of reach on Ortega, who is debuting at lightweight after a 455-day layoff." A Claude Sonnet 5.5 forecaster looked at Hooker's recent results instead: "Hooker has lost three straight by stoppage. Ortega has a long layoff and an unproven lightweight move but should have the grappling edge." The betting market is far less torn, with Hooker at 63%.

Where the crowd and the odds part ways

In three fights, the crowd picked against the betting market's favourite. The biggest gap is at heavyweight. Eight of 10 forecasters took Tallison Teixeira over Shamil Gaziev, though only at 52%, while the odds make Gaziev a 64% favourite.

Our model sides with the market, at 62% for Gaziev. A Claude Opus 5.5 forecaster made the case for Teixeira: "Younger and much longer at 83-inch reach; Gaziev was knocked down three times in his last three fights and fades late."

The other two disagreements are close to even on both sides. The crowd gave Aljamain Sterling 53% against Kevin Vallejos, whom the odds favour at 54%. It gave Shoaib Yousaf 55% against John Mitchell, the market's 56% favourite.

Opus and Fable go their own way

Claude Opus 5.5 was the dissenter on Sterling vs Vallejos. Two of its three forecasters took Vallejos, for an average of 52%.

Opus also leaned Santiago Luna over Aleksandre Topuria, two of three at 52%. Fable backed Topuria three of three, Sonnet split two and two, and our model has Topuria at 67%.

Beyond Hooker, Fable broke from the pack twice more. Two of its three forecasters took Amir Albazi over Alessandro Costa, at 52%, and John Mitchell over Shoaib Yousaf, at 51%. Every Sonnet and Opus forecaster went the other way in both fights.

FightAI crowdOur modelBetting market
Prochazka vs StirlingStirling 60%🔒Stirling 61%
Sterling vs VallejosSterling 53%🔒Vallejos 54%
Hooker vs OrtegaEven🔒Hooker 63%
Horiguchi vs AlmabayevHoriguchi 57%🔒Horiguchi 64%
Cannonier vs AliskerovAliskerov 77%🔒Aliskerov 72%
Topuria vs LunaTopuria 54%Topuria 67%Topuria 72%
Gaziev vs TeixeiraTeixeira 52%Gaziev 62%Gaziev 64%
Albazi vs CostaCosta 55%Costa 54%Even
Matthews vs AbdullayevMatthews 65%Matthews 62%Matthews 68%
Motta vs FanFan 62%Fan 69%Fan 61%
Nurgozhay vs LorenzNurgozhay 64%Nurgozhay 76%Nurgozhay 69%
Yousaf vs MitchellYousaf 55%—Mitchell 56%

Our model and the betting market as of Nov 21, 3:00 AM ET.

Every forecaster, fight by fight

Each dot is one AI forecaster, placed by the chance it gave its pick. Left of the middle line it picked the red-corner fighter, right of it the blue corner. Dots pile up in 5-point steps, Claude models above the line and GPT models below it.

Claude forecasterGPT forecasterAI crowd averageOur modelBetting market
AI crowd Stirling 60% 10 of 10
Market Stirling 61%
← ProchazkaStirling →
AI crowd Sterling 54% 8 of 10
Market Vallejos 54%
← SterlingVallejos →
AI crowd even
Market Hooker 63%
← HookerOrtega →
AI crowd Horiguchi 57% 10 of 10
Market Horiguchi 64%
← HoriguchiAlmabayev →
AI crowd Aliskerov 77% 10 of 10
Market Aliskerov 72%
← CannonierAliskerov →
AI crowd Topuria 54% 6 of 10
Our model Topuria 67% · Market Topuria 72%
← TopuriaLuna →
AI crowd Teixeira 52% 8 of 10
Our model Gaziev 62% · Market Gaziev 64%
← GazievTeixeira →
AI crowd Costa 55% 8 of 10
Our model Costa 54% · Market even
← AlbaziCosta →
AI crowd Matthews 65% 10 of 10
Our model Matthews 62% · Market Matthews 68%
← MatthewsAbdullayev →
AI crowd Fan 62% 10 of 10
Our model Fan 69% · Market Fan 61%
← MottaFan →
AI crowd Nurgozhay 64% 10 of 10
Our model Nurgozhay 76% · Market Nurgozhay 69%
← NurgozhayLorenz →
AI crowd Yousaf 55% 8 of 10
Market Mitchell 56%
← YousafMitchell →

Model by model

Model by model

Each model's own call, from its forecasters given no angle, next to the whole crowd. The number is the chance it gave its pick; red means it picked the red-corner fighter, blue the blue corner, and the deeper the colour, the surer it was.

FightAI crowdOpus 5.5Sonnet 5.5Fable 5.2
Prochazka v Stirling60 for Stirling63 for Stirling59 for Stirling58 for Stirling
Sterling v Vallejos54 for Sterling52 for Vallejos57 for Sterling54 for Sterling
Hooker v Ortega50 for neither53 for Ortega53 for Ortega59 for Hooker
Horiguchi v Almabayev57 for Horiguchi55 for Horiguchi57 for Horiguchi61 for Horiguchi
Cannonier v Aliskerov77 for Aliskerov76 for Aliskerov76 for Aliskerov79 for Aliskerov
Topuria v Luna54 for Topuria52 for Luna53 for Topuria61 for Topuria
Gaziev v Teixeira52 for Teixeira55 for Teixeira52 for Gaziev53 for Teixeira
Albazi v Costa55 for Costa55 for Costa60 for Costa52 for Albazi
Matthews v Abdullayev65 for Matthews63 for Matthews70 for Matthews62 for Matthews
Motta v Fan62 for Fan62 for Fan63 for Fan61 for Fan
Nurgozhay v Lorenz64 for Nurgozhay63 for Nurgozhay66 for Nurgozhay62 for Nurgozhay
Yousaf v Mitchell55 for Yousaf55 for Yousaf59 for Yousaf51 for Mitchell

How the AI crowd works

The crowd is 10 AI forecasters, played by Claude Opus 5.5, Claude Sonnet 5.5 and Claude Fable 5.2 from Anthropic. None of them was told how to weigh the fights: each got only the fact sheet and the question.

All of them read the same fact sheet: each fighter's record, size, career stats and UFC fights from our database, plus this week's news (the reports, and what the fighters and their coaches said), gathered once for each fight. None of them saw the betting odds, our model or each other's picks, and none could search the web. Half of them saw each fight with the fighters in the opposite order, so the order they're listed in can't tilt the result.

Each forecaster picked a winner in every fight and gave a chance. The crowd's number is the average of those chances. It's an experiment in how AI reads fights, not betting advice.

The AI crowd: every card so far, and how it works →

UFC Fight Night: Prochazka vs. Stirling: the full card, odds and results →

Subscribe free

Big Polymarket bets, line moves and favorite flips on the fights you follow, the second they happen. Plus our reads on the big fights before every card, and Parlay HQ to find the book that pays the most for your parlay. Free, one click with Google.

Continuing means you're 18 or older.

Use your email instead

FeedbackTell us what you think

Something broken, an idea, anything at all. We read every note.

We'll see which page you sent this from.