UFC Picks
Every priced UFC fight on the upcoming slate, grouped by card. Each scored by OctagonIQ's calibrated Monte Carlo (Brier 0.206, win-pick accuracy 78.2%) with predicted method and round. Value plays — where our model disagrees with the sportsbook market by 5+ percentage points — bubble to the top of each card. 10 value plays flagged across 2 cards.
- 57%LeanMainPrediction57%Melquizael Costa +140by Submission, Round 1 (29% chance of this exact outcome)vs Arnold Allen · Featherweight⚡ +15.2 Pp Valueon Melquizael Costa (+140) — same as the prediction
- 50%Coin FlipPrediction50%Juan Diaz +225by Decision (33% chance of this exact outcome)vs Malcolm Wellmaker · Bantamweight⚡ +19.6 Pp Valueon Juan Diaz (+225) — same as the prediction
- 52%Coin FlipPrediction52%Nicolle Caliari -225by Submission, Round 1 (36% chance of this exact outcome)vs Shauna Bannon · Women's Strawweight⚡ +12.4 Pp Valueon Shauna Bannon (+185) — model rates Bannon 48% but market only prices them at 35%
- 50%Coin FlipPrediction50%Tuco Tokkos +154by Decision (30% chance of this exact outcome)vs Ivan Erslan · Light Heavyweight⚡ +10.9 Pp Valueon Tuco Tokkos (+154) — same as the prediction
- 55%LeanPrediction55%Andre Petroski -218by Submission, Round 1 (29% chance of this exact outcome)vs Cody Brundage · Middleweight⚡ +8.9 Pp Valueon Cody Brundage (+180) — model rates Brundage 45% but market only prices them at 36%
- 57%LeanPrediction57%Alice Ardelean -218by Decision (57% chance of this exact outcome)vs Polyana Viana · Women's Strawweight⚡ +7.4 Pp Valueon Polyana Viana (+180) — model rates Viana 43% but market only prices them at 36%
- 63%HighPrediction63%Jacqueline Cavalcanti -170by Decision (63% chance of this exact outcome)vs Ketlen Vieira · Women's Bantamweight
- 53%Coin FlipPrediction53%Luis Gurule -115by Decision (53% chance of this exact outcome)vs Daniel Barez · Flyweight
- 56%LeanPrediction56%Benardo Sopaj -162by Decision (56% chance of this exact outcome)vs Timmy Cuamba · Bantamweight
- 56%LeanPrediction56%Rodolfo Bellato -106by KO/TKO, Round 1 (45% chance of this exact outcome)vs Modestas Bukauskas · Light Heavyweight
- 58%LeanPrediction58%Daniel Santos -170by KO/TKO, Round 1 (35% chance of this exact outcome)vs Dooho Choi · Featherweight
- 61%HighPrediction61%Tommy Gantt -175by Submission, Round 1 (48% chance of this exact outcome)vs Trey Ogden · Lightweight
- 52%Coin FlipPrediction52%Khaos Williams -125by KO/TKO, Round 1 (45% chance of this exact outcome)vs Nikolay Veretennikov · Welterweight
- 64%HighTitlePrediction64%Ilia Topuria -750by KO/TKO, Round 1 (52% chance of this exact outcome)vs Justin Gaethje · Lightweight⚡ +20.1 Pp Valueon Justin Gaethje (+525) — model rates Gaethje 36% but market only prices them at 16%
- 55%LeanPrediction55%Sean O'Malley -375by KO/TKO, Round 1 (48% chance of this exact outcome)vs Aiemann Zahabi · Bantamweight⚡ +20.0 Pp Valueon Aiemann Zahabi (+295) — model rates Zahabi 45% but market only prices them at 25%
- 66%HighPrediction66%Mauricio Ruffy -625by KO/TKO, Round 1 (59% chance of this exact outcome)vs Michael Chandler · Lightweight⚡ +16.2 Pp Valueon Michael Chandler (+455) — model rates Chandler 34% but market only prices them at 18%
- 56%LeanPrediction56%Bo Nickal -310by KO/TKO, Round 1 (39% chance of this exact outcome)vs Kyle Daukaus · Middleweight⚡ +15.7 Pp Valueon Kyle Daukaus (+250) — model rates Daukaus 44% but market only prices them at 29%
- 52%Coin FlipTitlePrediction52%Ciryl Gane -105by KO/TKO, Round 1 (43% chance of this exact outcome)vs Alex Pereira · Heavyweight
- 71%HighPrediction71%Josh Hokit -340by KO/TKO, Round 1 (65% chance of this exact outcome)vs Derrick Lewis · Heavyweight
How to read this page
Value Side is the side our model rates higher than the market is pricing. That can be the favorite or the underdog — it's about the gap between our probability and the market's, not who we predict to win outright. When the value side is the underdog (model gives them more chance than the line implies, but still under 50%), we tag it Underdog Value.
Most Likely is the model's top single outcome — predicted method (KO, Sub, or Decision), which side scores it, and the most likely round. Pulled from a 100,000-iteration Monte Carlo per fight.
Each fighter's win probability comes from a calibrated v2 engine (Brier 0.206 across the historical sample, 78.2% win-pick accuracy) that scores skill differential through a temperature-tuned sigmoid. The market's implied probability is computed by de-vigging the consensus sportsbook line. Value rows are sorted by gap size; everything else sits below as “Rest of the Card.” This page rebuilds every 30 minutes.
For research and entertainment. We don't accept bets. Read the full methodology.