Van vs Pantoja 2: Model Analysis

Event: Van vs Pantoja 2 Posted: September 23, 2026 · VAR Research First fight: September 20 2026, 01:00 UTC Card scope: 12 fights, lines locked at posted time Methodology: Methodology Model accuracy: Performance

Where the model diverges from consensus

Two matchups show the largest gap between our projected win probability and the public consensus.

JooSang Yoo vs Michael Aswell Jr.. Public consensus implies JooSang Yoo at 20.9%. Our model projects 66.2%. A 45-point gap, with JooSang Yoo materially underrated by the market.

Giga Chikadze vs Joanderson Brito. Public consensus implies Giga Chikadze at 23.1%. Our model projects 54.5%. A 31-point gap, with Giga Chikadze materially underrated by the market.

Full card projection

Matchup notes

Joshua Van vs Alexandre Pantoja. Joshua Van brings the cleaner striking and credible takedown defense (81%) to keep the fight standing. Joshua Van enters 5-0 in his last 5; Alexandre Pantoja is 3-2. Recent-form trajectory tilts the matchup.

Arman Tsarukyan vs Mauricio Ruffy. Arman Tsarukyan’s grappling pressure (3.3 takedowns / 15 min) projects to neutralize Mauricio Ruffy’s striking lane. Arman Tsarukyan holds the takedown-rate edge (3.3 vs 0.0 per 15 min).

Patricio Pitbull vs Dooho Choi. Dooho Choi enters 4-1 in his last 5; Patricio Pitbull is 2-2. Recent-form trajectory tilts the matchup. Dooho Choi outpaces Patricio Pitbull on strike volume (4.7 vs 2.7 per minute).

Gable Steveson vs Sean Sharaf. Gable Steveson absorbs notably less (0.0 vs 15.0 per minute), projecting better damage profile through three rounds.

Alonzo Menifield vs Iwo Baraniewski. Iwo Baraniewski outpaces Alonzo Menifield on strike volume (14.3 vs 3.8 per minute).

Marlon Vera vs Charles Jourdain. Striker-vs-striker matchup with Charles Jourdain carrying the volume edge (5.5 vs 4.2 sig strikes per minute). Charles Jourdain outpaces Marlon Vera on strike volume (5.5 vs 4.2 per minute).

Tai Tuivasa vs Robelis Despaigne. Robelis Despaigne absorbs notably less (2.5 vs 5.0 per minute), projecting better damage profile through three rounds.

Michael Aswell Jr. vs JooSang Yoo. Striker-vs-striker matchup, with JooSang Yoo’s accuracy edge (57% vs 45%) doing the work. JooSang Yoo absorbs notably less (5.0 vs 7.8 per minute), projecting better damage profile through three rounds.

Ryan Gandra vs Ozzy Diaz. Striker-vs-striker matchup with Ryan Gandra carrying the volume edge (13.0 vs 6.4 sig strikes per minute). Ryan Gandra enters 3-0 in his last 5; Ozzy Diaz is 1-3. Recent-form trajectory tilts the matchup.

Edmen Shahbazyan vs Brunno Ferreira. Edmen Shahbazyan enters 4-1 in his last 5; Brunno Ferreira is 2-3. Recent-form trajectory tilts the matchup.

Casey O’Neill vs Eduarda Moura. Style symmetry between Eduarda Moura and Casey O’Neill. The model declines to favor either side beyond noise.

Giga Chikadze vs Joanderson Brito. Style symmetry between Giga Chikadze and Joanderson Brito. The model declines to favor either side beyond noise.

How to read this

Projections come from VAR’s production UFC ensemble model, refreshed nightly. The model combines fighter performance metrics, simulation-based fight modeling, and historical opponent-strength signal, with conservative treatment of fighters who have limited recent data.

Confidence labels reflect projection spread:

• High: pick probability above 65%
• Medium: pick probability between 55 and 65%
• Coin flip: pick probability below 55%

Note: this analysis does not incorporate fight-week intelligence such as late injury reports or weight cut difficulty. Those signals are tracked through a separate process.

Model accuracy — live forward record

Every fight the production model priced before the bell since 2026-05-30, graded against the official result (n=186, through 2026-09-20; as of 2026-09-23):

• Straight-up winner accuracy: 65.0% (95% interval [58.0%, 71.6%])
• On the 180 fights with a closing line: the market’s favorite won 74.4%; Brier score model 0.221 vs de-vigged market 0.175 — the market is better calibrated.
• No betting tier has a validated positive return. VAR does not present UFC as a betting edge.

Full record, per card, with the withdrawn validation noted: Performance.

Results

Card record: 5-7 across 12 settled fights.

For research and informational purposes only. Probabilities reflect model output and may diverge from realized outcomes.