Skip to main content
Educational analyticsNot betting advice · research use only.
GameTime Picks
Today · Oct 30 · 10 eventsLatest results· Oct 29

UFC

UFC Fight Night: Moicano vs. Nolantimes in ET · updated Oct 29, 1:10 PM ET

Fight card & Official Forecasts

12 scheduled · 9 with a report · 9 with a supported read

Win chance is the fight model's published winner probability — not a sportsbook price. Method lean is the most likely way the fight ends, for either fighter, from the model's method head; it is not the chance that the pick wins that way, and method and round are not yet graded. Unavailable means too little tracked history to forecast. Paper and educational.

Model Performance: backtested on past cards and graded publicly beside the de-vigged sportsbook line, on a small live sample so far (the old moneyline model was retired) — see the graded record.

Live fight tracking for UFC is not available yet. This page shows the pregame card and forecasts; results and grading appear after the card is officially settled.

Next card

Card and model read · updated Oct 29, 1:10 PM ET

Fight-by-fight previewsEach bout's records, recent results and how the model expects it to end.

UFC Fight Night: Moicano vs. Nolan

Sat, Oct 31, 5:00 PM ET · Meta APEX · 12 bouts
Main event · Lightweight · 5 roundsRenato Moicano vs Tom NolanFull preview ▾
Full analysis →
Main event · Lightweight · 5 roundsGoes the distance 37.5%
Renato MoicanoRenato Moicano
vs
Tom NolanTom Nolan
Model pickTom Nolan · 75%Decision 37.5% · Ends in round 3 or later 57.0%
21-7-1Record11-1-0
W L L W WLast 5W W W W W
25%Win chance75%

From the tracked records (a summary, not the model's reasoning): Tom Nolan has won 5 of 6 tracked bouts (83%) to Moicano's 13 of 20 (65%); Nolan has the shorter tracked record (6 bouts to Moicano's 20). The model's method read has a decision as the most likely of three endings (37%), short of a majority.

How it ends
among fights that end with a winner
KO / TKO31.3%
Submission31.2%
Decision37.5%
Which round
R3+ includes every decision
25
R1
18
R2
57
R3+
Renato Moicano
Tracked record

3-2 in the last 5 tracked bouts. 9 of 13 wins came by finish (69%); 6 of 20 tracked fights reached the judges (30%).

Tendencies
· Most wins come inside the distance — 9 of 13, mostly by submission (2 KO/TKO, 7 submission)
· Most losses come inside the distance — 5 of 7 (3 KO/TKO, 2 submission)
Not established
? Neither a strength nor a weakness: 65% win rate across 20 tracked bouts (13-7)
WChris Duncan· SUB R2
LBeneil Dariush· DEC R3
LIslam Makhachev· SUB R1
WBenoit Saint Denis· KO R2
WJalin Turner· KO R2
Tom Nolan
Tracked record

5-0 in the last 5 tracked bouts. 2 of 5 wins came by finish (40%); 3 of 6 tracked fights reached the judges (50%).

Strengths · weaknesses
+ 83% win rate across 6 tracked bouts (5-1)
Not established
? Only 1 tracked loss — too few to say how fights are lost; absence of data, not absence of weakness
WFares Ziam· DEC R3
WCharlie Campbell· SUB R1
WViacheslav Borshchev· DEC R3
WAlex Reyes· DEC R3
WVictor Martinez· KO R1
Co-main event · Welterweight · 3 roundsRandy Brown vs Jacobe SmithFull preview ▾
Full analysis →
Welterweight · 3 roundsGoes the distance 49.9%
Randy BrownRandy Brown
vs
Jacobe SmithJacobe Smith
Model pickJacobe Smith · 58%Decision 49.9% · Ends in round 3 or later 57.9%
20-8-0Record13-0-0
L L W L WLast 5W W W
42%Win chance58%

From the tracked records (a summary, not the model's reasoning): Jacobe Smith has won 3 of 3 tracked bouts (100%) to Brown's 14 of 22 (64%); Smith has finished 3 of 3 wins (100%), and Brown has been finished in 5 of 8 losses (63%). The model's method read has a decision as the most likely of three endings (50%), short of a majority.

How it ends
among fights that end with a winner
KO / TKO32.0%
Submission18.1%
Decision49.9%
Which round
R3+ includes every decision
25
R1
17
R2
58
R3+
Randy Brown
Tracked record

2-3 in the last 5 tracked bouts. 7 of 14 wins came by finish (50%); 10 of 22 tracked fights reached the judges (45%).

Tendencies
· Most losses come inside the distance — 5 of 8 (3 KO/TKO, 2 submission)
· 3 submission wins across 22 tracked bouts
· 4 KO/TKO wins across 22 tracked bouts
Not established
? Neither a strength nor a weakness: 64% win rate across 22 tracked bouts (14-8)
LKevin Holland· DEC R3
LGabriel Bonfim· KO R2
WNicolas Dalby· KO R2
LBryan Battle· DEC R3
WElizeu Zaleski dos Santos· DEC R3
Jacobe Smith
Tracked record

3-0 in the last 3 tracked bouts. 3 of 3 wins came by finish (100%); 0 of 3 tracked fights reached the judges (0%).

Tendencies
· Most wins come inside the distance — 3 of 3, mostly by KO/TKO (2 KO/TKO, 1 submission)
Not established
? Only 3 tracked bouts — too few to call a strength or weakness (needs 5)
? No tracked losses — too few to say how fights are lost; absence of data, not absence of weakness
WJosiah Harrell· KO R1
WNiko Price· SUB R2
WPreston Parsons· KO R1
Bout 3 of 12 · Flyweight · 3 roundsOde' Osbourne vs Cody DurdenFull preview ▾
Full analysis →
Flyweight · 3 roundsGoes the distance 51.3%
Ode' OsbourneOde' Osbourne
vs
Cody DurdenCody Durden
Model pickOde' Osbourne · 56%Decision 51.3% · Ends in round 3 or later 58.9%
13-9-0Record18-11-1
L L W L LLast 5L W L L L
56%Win chance44%

From the tracked records (a summary, not the model's reasoning): Ode' Osbourne has finished 3 of 5 wins (60%), and Durden has been finished in 7 of 9 losses (78%). The model's method read makes a decision more likely than not (51%).

How it ends
among fights that end with a winner
KO / TKO30.5%
Submission18.3%
Decision51.3%
Which round
R3+ includes every decision
25
R1
16
R2
59
R3+
Ode' Osbourne
Tracked record

1-4 in the last 5 tracked bouts. 3 of 5 wins came by finish (60%); 5 of 13 tracked fights reached the judges (38%).

Strengths · weaknesses
− 62% of tracked bouts are losses (8 of 13)
Tendencies
· Most wins come inside the distance — 3 of 5, mostly by KO/TKO (3 KO/TKO, 0 submission)
· Most losses come inside the distance — 5 of 8 (2 KO/TKO, 3 submission)
LAlibi Idiris· DEC R3
LSteve Erceg· DEC R3
WLuis Gurule· KO R2
LRonaldo Rodriguez· DEC R3
LJafel Filho· SUB R1
Cody Durden
Tracked record

1-4 in the last 5 tracked bouts. 2 of 7 wins came by finish (29%); 7 of 16 tracked fights reached the judges (44%).

Strengths · weaknesses
− 56% of tracked bouts are losses (9 of 16)
Tendencies
· Most losses come inside the distance — 7 of 9 (2 KO/TKO, 5 submission)
LAlessandro Costa· SUB R2
WJafel Filho· DEC R3
LNyamjargal Tumendemberel· DEC R3
LAllan Nascimento· SUB R2
LJose Ochoa· KO R2
Bout 4 of 12 · W Bantamweight · 3 roundsYana Santos vs Luana SantosFull preview ▾
Full analysis →
W Bantamweight · 3 roundsGoes the distance 69.7%
Yana SantosYana Santos
vs
Luana SantosLuana Santos
Model pickLuana Santos · 80%Decision 69.7% · Ends in round 3 or later 77.7%
17-8-0Record11-2-0
W W W L LLast 5W W W L W
20%Win chance80%

From the tracked records (a summary, not the model's reasoning): Luana Santos has won 6 of 7 tracked bouts (86%) to Santos's 7 of 12 (58%). The model's method read makes a decision more likely than not (70%).

How it ends
among fights that end with a winner
KO / TKO16.1%
Submission14.1%
Decision69.7%
Which round
R3+ includes every decision
11
R1
11
R2
78
R3+
Yana Santos
Tracked record

3-2 in the last 5 tracked bouts. 0 of 7 wins came by finish (0%); 9 of 12 tracked fights reached the judges (75%).

Tendencies
· Wins rarely come inside the distance — 0 of 7
· Most losses come inside the distance — 3 of 5 (3 KO/TKO, 0 submission)
· Often goes the distance — 9 of 12 tracked fights reached the judges
Not established
? Neither a strength nor a weakness: 58% win rate across 12 tracked bouts (7-5)
WMacy Chiasson· DEC R3
WMiesha Tate· DEC R3
WChelsea Chandler· DEC R3
LKarol Rosa· DEC R3
LHolly Holm· DEC R3
Luana Santos
Tracked record

4-1 in the last 5 tracked bouts. 3 of 6 wins came by finish (50%); 4 of 7 tracked fights reached the judges (57%).

Strengths · weaknesses
+ 86% win rate across 7 tracked bouts (6-1)
Not established
? Only 1 tracked loss — too few to say how fights are lost; absence of data, not absence of weakness
WKarol Rosa· DEC R3
WMelissa Croden· DEC R3
WTainara Lisboa· SUB R2
LCasey O'Neill· DEC R3
WMariya Agapova· SUB R1
Bout 5 of 12 · Welterweight · 3 roundsJean-Paul Lebosnoyani vs Farman HasanovFull preview ▾
Full analysis →
Welterweight · 3 rounds
Jean-Paul LebosnoyaniJean-Paul Lebosnoyani
vs
Farman HasanovFarman Hasanov
11-2-0Record5-0-0
W WLast 5W

Neither fighter has enough UFC history in our corpus to build a read from.

Jean-Paul Lebosnoyani
Tracked record

2-0 in the last 2 tracked bouts. 0 of 2 wins came by finish (0%); 2 of 2 tracked fights reached the judges (100%).

Not established
? Only 2 tracked bouts — too few to name a strength, weakness or tendency
WSeokhyeon Ko· DEC R3
WPhil Rowe· DEC R3
Farman Hasanov
Tracked record

1-0 in the last 1 tracked bout. 0 of 1 win came by finish (0%); 1 of 1 tracked fight reached the judges (100%).

Not established
? Only 1 tracked bout — too few to name a strength, weakness or tendency
WEric Nolan· DEC R3
Bout 6 of 12 · Featherweight · 3 roundsDakota Hope vs Francis MarshallFull preview ▾
Full analysis →
Featherweight · 3 roundsGoes the distance 53.3%
Dakota HopeDakota Hope
vs
Francis MarshallFrancis Marshall
Model pickFrancis Marshall · 73%Decision 53.3% · Ends in round 3 or later 61.0%
11-2-0Record10-3-0
LLast 5W W L W L
27%Win chance73%

From the tracked records (a summary, not the model's reasoning): Francis Marshall has won 4 of 7 tracked bouts (57%) to Hope's 0 of 1 (0%). The model's method read makes a decision more likely than not (53%).

How it ends
among fights that end with a winner
KO / TKO28.1%
Submission18.6%
Decision53.3%
Which round
R3+ includes every decision
24
R1
15
R2
61
R3+
Dakota Hope
Tracked record

0-1 in the last 1 tracked bout. No tracked wins; 1 of 1 tracked fight reached the judges (100%).

Not established
? Only 1 tracked bout — too few to name a strength, weakness or tendency
LKai Kamaka III· DEC R3
Francis Marshall
Tracked record

3-2 in the last 5 tracked bouts. 2 of 4 wins came by finish (50%); 4 of 7 tracked fights reached the judges (57%).

Not established
? Neither a strength nor a weakness: 57% win rate across 7 tracked bouts (4-3)
WLucas Brennan· DEC R3
WErik Silva· SUB R1
LMairon Santos· DEC R3
WDennis Buzukja· DEC R3
LIsaac Dulgarian· KO R1
Bout 7 of 12 · Welterweight · 3 roundsTheodor Berggren vs Rodrigo SezinandoFull preview ▾
Full analysis →
Welterweight · 3 rounds
Theodor BerggrenTheodor Berggren
vs
Rodrigo SezinandoRodrigo Sezinando
8-4-0Record9-2-0
LLast 5L

Neither fighter has enough UFC history in our corpus to build a read from.

Theodor Berggren
Tracked record

0-1 in the last 1 tracked bout. No tracked wins; 0 of 1 tracked fight reached the judges (0%).

Not established
? Only 1 tracked bout — too few to name a strength, weakness or tendency
LDaniil Donchenko· KO R2
Rodrigo Sezinando
Tracked record

0-1 in the last 1 tracked bout. No tracked wins; 0 of 1 tracked fight reached the judges (0%).

Not established
? Only 1 tracked bout — too few to name a strength, weakness or tendency
LDaniil Donchenko· KO R1
Bout 8 of 12 · Featherweight · 3 roundsJulian Erosa vs JeongYeong LeeFull preview ▾
Full analysis →
Featherweight · 3 roundsGoes the distance 46.1%
Julian ErosaJulian Erosa
vs
JeongYeong LeeJeongYeong Lee
Model pickJeongYeong Lee · 57%Decision 46.1% · Ends in round 3 or later 54.5%
31-14-0Record11-3-0
L L W W WLast 5L L W W
43%Win chance57%

From the tracked records (a summary, not the model's reasoning): JeongYeong Lee has the shorter tracked record (4 bouts to Erosa's 18). The model's method read has a decision as the most likely of three endings (46%), short of a majority.

How it ends
among fights that end with a winner
KO / TKO26.7%
Submission27.3%
Decision46.1%
Which round
R3+ includes every decision
29
R1
17
R2
55
R3+
Julian Erosa
Tracked record

3-2 in the last 5 tracked bouts. 6 of 9 wins came by finish (67%); 5 of 18 tracked fights reached the judges (28%).

Tendencies
· Most wins come inside the distance — 6 of 9, mostly by submission (2 KO/TKO, 4 submission)
· Most losses come inside the distance — 7 of 9 (7 KO/TKO, 0 submission)
Not established
? Neither a strength nor a weakness: 50% win rate across 18 tracked bouts (9-9)
LLerryan Douglas· KO R1
LMelquizael Costa· DEC R3
WDarren Elkins· KO R1
WChristian Rodriguez· SUB R1
WRicardo Ramos· SUB R1
JeongYeong Lee
Tracked record

2-2 in the last 4 tracked bouts. 0 of 2 wins came by finish (0%); 3 of 4 tracked fights reached the judges (75%).

Not established
? Only 4 tracked bouts — too few to call a strength or weakness (needs 5)
? Only 2 tracked losses — too few to say how fights are lost; absence of data, not absence of weakness
LDaniel Santos· DEC R3
LHyder Amil· KO R1
WBlake Bilder· DEC R3
WYizha· DEC R3
Bout 9 of 12 · Middleweight · 3 roundsMickey Gall vs Zach ReeseFull preview ▾
Full analysis →
Middleweight · 3 roundsGoes the distance 39.9%
Mickey GallMickey Gall
vs
Zach ReeseZach Reese
Model pickZach Reese · 56%Decision 39.9% · Ends in round 3 or later 47.5%
7-7-0Record10-4-0
L L L L WLast 5L L W W L
44%Win chance56%

The model reads it 56% — nothing in either tracked record separates them cleanly, so the number rests on the model's wider inputs rather than a headline stat.

How it ends
among fights that end with a winner
KO / TKO27.2%
Submission32.9%
Decision39.9%
Which round
R3+ includes every decision
33
R1
20
R2
47
R3+
Mickey Gall
Tracked record

1-4 in the last 5 tracked bouts. 5 of 6 wins came by finish (83%); 5 of 13 tracked fights reached the judges (38%).

Tendencies
· Most wins come inside the distance — 5 of 6, mostly by submission (0 KO/TKO, 5 submission)
Not established
? Neither a strength nor a weakness: 46% win rate across 13 tracked bouts (6-7)
LRamiz Brahimaj· KO R1
LBassil Hafez· DEC R3
LMike Malott· KO R1
LAlex Morono· DEC R3
WJordan Williams· SUB R1
Zach Reese
Tracked record

2-3 in the last 5 tracked bouts. 2 of 4 wins came by finish (50%); 3 of 8 tracked fights reached the judges (38%).

Tendencies
· Most losses come inside the distance — 3 of 4 (3 KO/TKO, 0 submission)
Not established
? Neither a strength nor a weakness: 50% win rate across 8 tracked bouts (4-4)
LRyan Gandra· KO R1
LMichel Pereira· DEC R3
WJackson McVey· SUB R2
WDusko Todorovic· DEC R3
LAzamat Bekoev· KO R1
Bout 10 of 12 · Middleweight · 3 roundsJoe Kropschot vs Nick KleinFull preview ▾
Full analysis →
Middleweight · 3 rounds
JKJoe Kropschot9-3-0
vs
Nick KleinNick Klein
9-3-0Record6-3-0
—Last 5L L

Neither fighter has enough UFC history in our corpus to build a read from.

Nick Klein
Tracked record

0-2 in the last 2 tracked bouts. No tracked wins; 0 of 2 tracked fights reached the judges (0%).

Not established
? Only 2 tracked bouts — too few to name a strength, weakness or tendency
LAndrey Pulyaev· KO R2
LMansur Abdul-Malik· KO R2
Bout 11 of 12 · W Strawweight · 3 roundsPiera Rodriguez vs Talita AlencarFull preview ▾
Full analysis →
W Strawweight · 3 roundsGoes the distance 77.3%
Piera RodriguezPiera Rodriguez
vs
Talita AlencarTalita Alencar
Model pickPiera Rodriguez · 56%Decision 77.3% · Ends in round 3 or later 83.9%
12-2-0Record8-1-1
W W W L WLast 5W W W L W
56%Win chance44%

The model reads it 56% — nothing in either tracked record separates them cleanly, so the number rests on the model's wider inputs rather than a headline stat.

How it ends
among fights that end with a winner
KO / TKO10.2%
Submission12.5%
Decision77.3%
Which round
R3+ includes every decision
7
R1
9
R2
84
R3+
Piera Rodriguez
Tracked record

4-1 in the last 5 tracked bouts. 0 of 5 wins came by finish (0%); 5 of 6 tracked fights reached the judges (83%).

Strengths · weaknesses
+ 83% win rate across 6 tracked bouts (5-1)
Tendencies
· Wins rarely come inside the distance — 0 of 5
· Often goes the distance — 5 of 6 tracked fights reached the judges
Not established
? Only 1 tracked loss — too few to say how fights are lost; absence of data, not absence of weakness
WSam Hughes· DEC R3
WKetlen Souza· DEC R3
WJosefine Knutsson· DEC R3
LGillian Robertson· SUB R2
WSam Hughes· DEC R3
Talita Alencar
Tracked record

4-1 in the last 5 tracked bouts. 1 of 4 wins came by finish (25%); 4 of 5 tracked fights reached the judges (80%).

Strengths · weaknesses
+ 80% win rate across 5 tracked bouts (4-1)
Tendencies
· Often goes the distance — 4 of 5 tracked fights reached the judges
Not established
? Only 1 tracked loss — too few to say how fights are lost; absence of data, not absence of weakness
WJulia Polastri· DEC R3
WAriane Carnelossi· SUB R3
WVanessa Demopoulos· DEC R3
LStephanie Luciano· DEC R3
WRayanne dos Santos· DEC R3
Bout 12 of 12 · W Flyweight · 3 roundsTainara Lisboa vs Lucia SzabováFull preview ▾
Full analysis →
W Flyweight · 3 roundsGoes the distance 47.0%
Tainara LisboaTainara Lisboa
vs
LSLucia Szabová12-0-0
Model pickTainara Lisboa · 54%Decision 47.0% · Ends in round 3 or later 56.4%
7-4-0Record12-0-0
L L W WLast 5—
54%Win chance46%
How it ends
among fights that end with a winner
KO / TKO20.6%
Submission32.4%
Decision47.0%
Which round
R3+ includes every decision
28
R1
15
R2
56
R3+
Tainara Lisboa
Tracked record

2-2 in the last 4 tracked bouts. 1 of 2 wins came by finish (50%); 1 of 4 tracked fights reached the judges (25%).

Not established
? Only 4 tracked bouts — too few to call a strength or weakness (needs 5)
? Only 2 tracked losses — too few to say how fights are lost; absence of data, not absence of weakness
LMelissa Croden· KO R3
LLuana Santos· SUB R2
WRavena Oliveira· DEC R3
WJessica-Rose Clark· SUB R3
What is modelled, and what is not

Three markets publish — winner, method and ending round — each tested separately by walking forward through 3,557 held-out fights from a corpus of 8,642 bouts (Mar 1994 to Aug 2026). A head that fails its bar is withheld while the others still publish.

MarketModelBaselineLog loss
Winner60.6%50.0%0.661 vs 0.693
Method52.7%46.7%0.969 vs 1.025
Ending round60.6%55.3%0.915 vs 0.955

Accuracy is measured against a base-rate baseline. Paper and educational — research estimates, never advice, and never presented as an advantage over the sportsbook price.

Moneyline: This card publishes the model's own probabilities and carries no price beside them. UFC prices are captured separately and live in the odds and moneyline-grading artifacts; they are not joined into this document.

Schedule source: ESPN public scoreboard

Play the card story — the main event, step by step

Simulation story

7 chapters · read from the published artifact
Skip to the report ↓
› Loading the matchup model› Reading the outcome distribution› Preparing the score scenariosPress Play to step through what the model expects, chapter by chapter, or read the report below.

UFC Fight Night: Moicano vs. Nolan

12 bouts at Meta APEX. The model read 9 of them.

model ufc-fight-model@e657fc40b64dno run count recordedproduced Oct 29, 1:10 PM ET

Winner, method and finishing round for every bout with enough tracked fighter history; the rest are marked Unavailable with the reason. Paper and educational.

What changed, and what is still refused
The de-vigged-price read that ran until Jul 23, 2026 was retired: it restated the sportsbook rather than forming an opinion. What publishes now is a fight model trained on 8,642 decisive bouts, with each of its three markets tested separately against a base-rate baseline. Posted fight-winner prices are captured, but no paper cards are shown here while UFC is not cleared for forward-looking model cards — and since Aug 22, 2026 the model IS scored against the de-vigged line, bout by bout, in the graded record below: both probabilities recorded before each card, graded on the official result. The sample is far too small to support any claim in either direction, and the cumulative comparison currently favours the market. The settled record from the retired era is kept below, behind its own label.

Record

Current era · fight model vs de-vigged price
Picks vs outcomes · 90 graded

How the model's picks actually turned out

Fight-winner picks: the model's chosen fighter and its probability, graded against the official result.

Full record →
55 hit · 35 missed1 void — a condition that did not hold is never scored as a miss61.1% hit rate

90 graded picks is still a small sample. A hit rate over this many outcomes has a wide enough margin of error to be consistent with almost any true accuracy.

The market's own de-vigged probability for the same bout is shown alongside. This is the only sport here where the two are recorded together.

DateEventModel saidWhat happenedMarket priced itResult
2026-10-24Movsar Evloev vs Alexander VolkanovskiMovsar Evloev · 69.4%Alexander Volkanovski50.4%MISS
2026-10-24Petr Yan vs Merab DvalishviliPetr Yan · 55.3%Petr Yan57.8%HIT
2026-10-24Alexander Volkov vs Rizvan KunievAlexander Volkov · 61.4%Alexander Volkov52.2%HIT
2026-10-24Dominick Reyes vs Azamat MurzakanovDominick Reyes · 51.9%Dominick Reyes34.9%HIT
2026-10-24Abdul-Rakhman Yakhyaev vs Nikita KrylovAbdul-Rakhman Yakhyaev · 74.9%Abdul-Rakhman Yakhyaev80.8%HIT
2026-10-24Cam Rowston vs Abus MagomedovCam Rowston · 68.8%Abus Magomedov53.7%MISS

Showing the 6 most recent of 90 graded.

Settled archiveArchive · no live coverageretired moneyline era — one settled card
Officially settled June 15, 2026
UFC Freedom 250: Topuria vs. Gaethje · officially settledFINAL
6-1
Moneyline record
86%
Moneyline accuracy
0-4
Suggested cards
5/6
Goes-distance (model)
Pick vs official result
Diego Lopes vs Steve Garcia Jr.Pick Diego Lopes 59% (-162) · winner Diego Lopes by finish R2 2:42
WIN
Bo Nickal vs Kyle DaukausPick Bo Nickal 74% (-345) · winner Bo Nickal by finish R1 4:34
WIN
Mauricio Ruffy vs Michael ChandlerPick Mauricio Ruffy 84% (-700) · winner Mauricio Ruffy by finish R1 4:29
WIN
Derrick Lewis vs Josh HokitPick Josh Hokit 77% (+320) · winner Josh Hokit by finish R2 4:09
WIN
Sean O'Malley vs Aiemann ZahabiPick Sean O'Malley 78% (-440) · winner Sean O'Malley by finish R2 4:02
WIN
Alex Pereira vs Ciryl GanePick Ciryl Gane 50% (-110) · winner Ciryl Gane by finish R2 1:27
WIN
Ilia Topuria vs Justin GaethjePick Ilia Topuria 80% (-520) · winner Justin Gaethje by finish R4 5:00
LOSS
Suggested cards · 0-4
Conservative card · 2 legsLOST
Mauricio Ruffy ✓Ilia Topuria ✕
Busted by: Ilia Topuria
Balanced card · 2 legsLOST
Ilia Topuria ✕Sean O'Malley ✓
Busted by: Ilia Topuria
High-risk card · 4 legsLOST
Mauricio Ruffy ✓Ilia Topuria ✕Sean O'Malley ✓Josh Hokit ✓
Busted by: Ilia Topuria
Longshot card · 5 legsLOST
Mauricio Ruffy ✓Ilia Topuria ✕Sean O'Malley ✓Josh Hokit ✓Bo Nickal ✓
Busted by: Ilia Topuria

Settled from the official ESPN MMA scoreboard. Winners + ending round/time + scheduled rounds are official from the ESPN MMA feed. Specific finish method (KO/TKO vs submission) is not exposed by the connected feed, so method grading is at the finish-vs-decision level only; KO-vs-submission is needs_review. Expanded model-only props graded for calibration only — no betting P&L. Paper-only educational tracking.

Source detailsESPN MMA scoreboard (site.api.espn.com/apis/site/v2/sports/mma/ufc/scoreboard, event 600058854, STATUS_FINAL)

This is one settled event (7 graded fights). A single-card record is an outcome log, not model validation — the moneyline model was retired unvalidated.

The two eras never share a metric. The current record grades a three-head fight model against the de-vigged price recorded before each card; the archive is the retired read's outcome log from before any model was scored against anything. Adding them together would average two different questions.

Model health · UFC

open for the live record behind each callFight model Tested on past seasonsLive record Watch

Model status · UFC

What the statuses mean →
  • Fight modelTested on past seasons
    Backtest passed on held-out fights

    On 3,557 fights held out of the fit, log loss (lower is better) was 0.661 against 0.693 for a coin flip on the winner, 0.969 against 1.025 for the method base rate and 0.915 against 0.955 for the round base rate. These are point estimates against simple baselines, with no uncertainty interval, and they are not a comparison with sportsbook prices.

    What does this mean?

    Before it went live, this model was scored on past seasons it had never seen and cleared bars set in advance against simpler baselines. That is a bar, not a promise, and not a claim that it beats sportsbook prices.

  • Live recordWatch
    Watch · not yet distinguishable from a coin flip

    Measured by log loss (lower is better) over 90 graded: 0.715 for this call against 0.693 for a coin flip, a difference of +0.021 (95% interval −0.072 to +0.127). The interval includes zero, so this call cannot yet be told apart from a coin flip.

    What does this mean?

    Over the games graded so far, this call is slightly behind its floor, but not by enough to be sure it is worse. It keeps publishing while the record grows.

UFC 329: McGregor vs. Holloway 2 (July 11, 2026) was listed with market-implied reads only before the event; no model picks were published for it and no official settlement was ingested, so no record is claimed for it.