Left it all in the Octagon 👏 Roberto Soldic earns the UD victory in his UFC debut over a hard-fought 15 minutes! [ #UFC332 | LIVE NOW on @ParamountPlus and @CBS ]
View video on X ↗Roberto Soldić defeats Khaos Williams by unanimous decision
Unanimous decision
Round 3 · 5:00
Williams vs Soldić — Welterweight · UFC 332: Silva vs. Wang
Predictions summary
Analyst Picks
(10) 24%
76% (31)
AI Predictions
42%
58%
Market OddsComing soonNo forecast publishedUnavailable right nowBook prices available in Market
Checking latest live market odds.
What happened
The result, the defining moments, and what the verdict means.
Williams stung Soldić a couple of times early in the first round, and Soldić turned to wrestling in the back half of the round.
From the second round Soldić took control, hurting Williams on the feet and the ground.
All three judges scored it for Soldić, by 29-28, 29-27 and 29-27.
- primaryUFC 332 main card results
Pre-fight analysis — how we saw it going in
Case for Williams
Williams is 16-5-0 with nine of his wins by knockout, and he snapped a two-fight skid by finishing Nikolay Veretennikov with punches in the first round in May 2026 after a decision loss to Andreas Gustafsson and a submission loss to Gabriel Bonfim. When his hands are landing clean, his power alone can end a fight in one exchange.
Case for Soldić
Soldic brings one of the most finish-heavy records on the card at 21-4-0 with 18 knockouts, most recently a first-round KO of Saygid Guseyn Arslanaliev in February 2025, built entirely outside the UFC. His last six fights carry his only two recent blemishes — a no-contest against Murad Ramazanov in December 2022 and a stoppage loss to Zebaztian Kadestam in May 2023 — either side of four finishes.
What We Were Watching For
- Whether Soldic's heavy hands find the same target early that produced 18 of his 21 career wins.
- Williams' chin and recovery instincts if hurt, given two of his last three losses came by stoppage or submission.
- How Soldic's power translates in his move to the UFC's deeper welterweight competition, against a fighter already tested at this level.
- Whether the fight stays standing, where both have finished the bulk of their wins.
Records & career stats
- 16-5-0
- Record
- 21-4-0
- —
- Recent formRecent formWin–loss record over the fighter’s last five bouts, newest first, as carried in their UFC/FightMetric career stats.
- Source pending
- United States
- Nationality
- Source pending
- 32
- Age
- 31
- —
- StanceStanceWhich side a fighter leads from — a striking term, not a religious one. Orthodox: right-handed, left foot and hand forward (the common default). Southpaw: the mirror image, right side forward (usually a left-hander). Switch: changes between the two during a fight.
- Source pending
- 52%
- Takedown defenseTD def.Takedown defenseThe percentage of opponents’ takedown attempts that are stuffed. Higher means harder to put on the mat. From UFC/FightMetric.
- Source pending
- 09:16
- Avg. fight timeAvg. timeAverage fight timeThe mean length of the fighter’s bouts (minutes:seconds) — a rough read on whether they tend to finish early or go the distance. From UFC/FightMetric.
- 15:00
- Murcielago MMA
- Team
- RRC Gym and UFD Gym
Career stats per UFC.com; recent form is each fighter's last five bouts. Record is as of fight night; career stats, recent form and win totals are the latest on file and may include this fight. Bars compare each stat on a fixed scale; the “Edge” marker flags the leading corner where the gap is meaningful. The snapshot plots five career rates — output, striking defense, durability (strikes absorbed, inverted), takedown defense and finish rate — each normalised on its own scale.
Videos
Outcome footage, post-fight coverage, and the pre-fight lead-up.
After the fight
Comments
Who Called It?
How the analysts' picks held up once the cage door closed.
(10) 24%
LWilliams
76% (31)
SoldićW
Fite Feed
Current pick evidence
Picked: Khaos Williams · KO/TKO · Round 2
Fight result: Roberto Soldić · Decision
Sees Williams landing a big right hand in a striking fight, while noting he is not yet convinced enough to rule out changing his pick.
Track record: winner called in 24 of 37 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 64.9% (24 hit, 13 miss, across 37 resolved calls). Method Accuracy 60.9% (14 hit, 9 miss, across 23 method-scored calls on 37 resolved calls). Round Accuracy 21.4% (3 hit, 11 miss, across 14 round-scored calls on 37 resolved calls). Underdog Accuracy 40.0% (2 hit, 3 miss, across 5 underdog calls on 37 resolved calls).
- Winner Accuracy 64.9% 24 13
- Method Accuracy 60.9% 14 9
- Round Accuracy 21.4% 3 11
- Underdog Accuracy 40.0% 2 3
Kunath
Current pick evidence
Picked: Khaos Williams · KO/TKO
Fight result: Roberto Soldić · Decision
Kunath selects Khaos Williams by ko/tko.
Track record: winner called in 38 of 65 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 58.5% (38 hit, 27 miss, across 65 resolved calls). Method Accuracy 56.7% (17 hit, 13 miss, across 30 method-scored calls on 65 resolved calls). Round Accuracy 40.0% (2 hit, 3 miss, across 5 round-scored calls on 65 resolved calls). Underdog Accuracy 25.0% (3 hit, 9 miss, across 12 underdog calls on 65 resolved calls).
- Winner Accuracy 58.5% 38 27
- Method Accuracy 56.7% 17 13
- Round Accuracy 40.0% 2 3
- Underdog Accuracy 25.0% 3 9
Angelo Bodetti
Current pick evidence
Picked: Khaos Williams
Fight result: Roberto Soldić · Decision
Bodetti favors Williams’s knockout power, durability and UFC experience. He sees Soldic as dangerous but questions how the debut and elevation will affect him.
Track record: winner called in 29 of 50 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 58.0% (29 hit, 21 miss, across 50 resolved calls). Method Accuracy 60.0% (3 hit, 2 miss, across 5 method-scored calls on 50 resolved calls). Round Accuracy 100.0% (1 hit, 0 miss, across 1 round-scored calls on 50 resolved calls). Underdog Accuracy 40.0% (2 hit, 3 miss, across 5 underdog calls on 50 resolved calls).
- Winner Accuracy 58.0% 29 21
- Method Accuracy 60.0% 3 2
- Round Accuracy 100.0% 1
- Underdog Accuracy 40.0% 2 3
The Finz Chats
Current pick evidence
Picked: Khaos Williams · KO/TKO · Round 1
Fight result: Roberto Soldić · Decision
The Finz Chats selects Khaos Williams by ko/tko in round 1.
Track record: winner called in 12 of 22 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 54.5% (12 hit, 10 miss, across 22 resolved calls). Method Accuracy 42.9% (3 hit, 4 miss, across 7 method-scored calls on 22 resolved calls). Round Accuracy 100.0% (1 hit, 0 miss, across 1 round-scored calls on 22 resolved calls). Underdog Accuracy 66.7% (2 hit, 1 miss, across 3 underdog calls on 22 resolved calls).
- Winner Accuracy 54.5% 12 10
- Method Accuracy 42.9% 3 4
- Round Accuracy 100.0% 1
- Underdog Accuracy 66.7% 2 1
Chris Schweppe
Current pick evidence
Picked: Khaos Williams · KO/TKO · Round 1
Fight result: Roberto Soldić · Decision
Schweppe picks Khaos Williams to win by first-round knockout.
Track record: winner called in 53 of 99 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 53.5% (53 hit, 46 miss, across 99 resolved calls). Method Accuracy 47.2% (25 hit, 28 miss, across 53 method-scored calls on 99 resolved calls). Round Accuracy 33.3% (10 hit, 20 miss, across 30 round-scored calls on 99 resolved calls). Underdog Accuracy 33.3% (10 hit, 20 miss, across 30 underdog calls on 99 resolved calls).
- Winner Accuracy 53.5% 53 46
- Method Accuracy 47.2% 25 28
- Round Accuracy 33.3% 10 20
- Underdog Accuracy 33.3% 10 20
D.Rose
Current pick evidence
Picked: Khaos Williams · KO/TKO · Round 2
Fight result: Roberto Soldić · Decision
Respects Soldic’s wrestling but favors Williams’s power if Soldic trades with him, calling a second-round knockout.
Track record: winner called in 11 of 21 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 52.4% (11 hit, 10 miss, across 21 resolved calls). Method Accuracy 80.0% (4 hit, 1 miss, across 5 method-scored calls on 21 resolved calls). Round Accuracy 66.7% (2 hit, 1 miss, across 3 round-scored calls on 21 resolved calls). Underdog Accuracy 100.0% (1 hit, 0 miss, across 1 underdog calls on 21 resolved calls).
- Winner Accuracy 52.4% 11 10
- Method Accuracy 80.0% 4 1
- Round Accuracy 66.7% 2 1
- Underdog Accuracy 100.0% 1
Gerardo Rivas
Current pick evidence
Picked: Khaos Williams · KO/TKO · Round 1
Fight result: Roberto Soldić · Decision
Expects Williams’s power and reach advantage to catch Soldic early, and doubts Soldic’s durability.
Track record: winner called in 7 of 15 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 46.7% (7 hit, 8 miss, across 15 resolved calls). Method Accuracy 33.3% (1 hit, 2 miss, across 3 method-scored calls on 15 resolved calls). Round Accuracy 0.0% (0 hit, 2 miss, across 2 round-scored calls on 15 resolved calls). Underdog Accuracy 33.3% (1 hit, 2 miss, across 3 underdog calls on 15 resolved calls).
- Winner Accuracy 46.7% 7 8
- Method Accuracy 33.3% 1 2
- Round Accuracy 0.0% 2
- Underdog Accuracy 33.3% 1 2
Timothy Wheaton
Current pick evidence
Picked: Khaos Williams
Fight result: Roberto Soldić · Decision
Timothy Wheaton leans Khaos Williams, describing a decision or late-stoppage path while leaving the exact method open.
Track record: winner called in 4 of 9 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 44.4% (4 hit, 5 miss, across 9 resolved calls). Method Accuracy 33.3% (1 hit, 2 miss, across 3 method-scored calls on 9 resolved calls). Round Accuracy: No qualifying picks. Underdog Accuracy: No underdog calls with a known pre-fight price.
- Winner Accuracy 44.4% 4 5
- Method Accuracy 33.3% 1 2
- Round AccuracyNamed rounds — none on a correct call yet
- Underdog AccuracyNo underdog calls with a known pre-fight price
Chris Cross
Current pick evidence
Picked: Khaos Williams · KO/TKO
Fight result: Roberto Soldić · Decision
Picks Khaos Williams to win, probably by KO, while warning that Roberto Soldic's 18 knockouts make him dangerous.
Track record: winner called in 8 of 20 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 40.0% (8 hit, 12 miss, across 20 resolved calls). Method Accuracy 25.0% (1 hit, 3 miss, across 4 method-scored calls on 20 resolved calls). Round Accuracy 0.0% (0 hit, 1 miss, across 1 round-scored calls on 20 resolved calls). Underdog Accuracy 0.0% (0 hit, 1 miss, across 1 underdog calls on 20 resolved calls).
- Winner Accuracy 40.0% 8 12
- Method Accuracy 25.0% 1 3
- Round Accuracy 0.0% 1
- Underdog Accuracy 0.0% 1
Carlos Cano
Current pick evidence
Picked: Khaos Williams · Dec
Fight result: Roberto Soldić · Decision
Favors Williams’s punching power, defense and UFC experience over the debuting Soldic.
Track record: winner called in 3 of 10 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 30.0% (3 hit, 7 miss, across 10 resolved calls). Method Accuracy 50.0% (1 hit, 1 miss, across 2 method-scored calls on 10 resolved calls). Round Accuracy: No qualifying picks. Underdog Accuracy 0.0% (0 hit, 1 miss, across 1 underdog calls on 10 resolved calls).
- Winner Accuracy 30.0% 3 7
- Method Accuracy 50.0% 1 1
- Round AccuracyNamed rounds — none on a correct call yet
- Underdog Accuracy 0.0% 1
Hank
Current pick evidence
Picked: Roberto Soldić · KO/TKO · Round 2
Fight result: Roberto Soldić · Decision
Favors Soldic’s technique and forward pressure over Williams’s boxing.
Track record: winner called in 11 of 12 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 91.7% (11 hit, 1 miss, across 12 resolved calls). Method Accuracy 90.9% (10 hit, 1 miss, across 11 method-scored calls on 12 resolved calls). Round Accuracy 44.4% (4 hit, 5 miss, across 9 round-scored calls on 12 resolved calls). Underdog Accuracy: No underdog calls with a known pre-fight price.
- Winner Accuracy 91.7% 11 1
- Method Accuracy 90.9% 10 1
- Round Accuracy 44.4% 4 5
- Underdog AccuracyNo underdog calls with a known pre-fight price
Bedtime MMA
Current pick evidence
Picked: Roberto Soldić · KO/TKO · Round 1
Fight result: Roberto Soldić · Decision
Bedtime favors Soldic’s more technical striking and left-hand counter, expecting him to draw reactions from Williams and land the knockout shot. He picks a first-round finish but worries about Williams’s knockout power and how Soldic will handle his UFC debut.
“going to pick him to win this one by round one KO.”
* He remains concerned that Williams could knock Soldic out.
Track record: winner called in 132 of 185 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 71.4% (132 hit, 53 miss, across 185 resolved calls). Method Accuracy 61.9% (60 hit, 37 miss, across 97 method-scored calls on 185 resolved calls). Round Accuracy 40.7% (11 hit, 16 miss, across 27 round-scored calls on 185 resolved calls). Underdog Accuracy 48.7% (19 hit, 20 miss, across 39 underdog calls on 185 resolved calls).
- Winner Accuracy 71.4% 132 53
- Method Accuracy 61.9% 60 37
- Round Accuracy 40.7% 11 16
- Underdog Accuracy 48.7% 19 20
FightIQ
Current pick evidence
Picked: Roberto Soldić · KO/TKO
Fight result: Roberto Soldić · Decision
FightIQ's public record lists Roberto Soldic as its pick over Khaos Williams.
Track record: winner called in 159 of 227 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 70.0% (159 hit, 68 miss, across 227 resolved calls). Method Accuracy 39.9% (59 hit, 89 miss, across 148 method-scored calls on 227 resolved calls). Round Accuracy: No round picks. Underdog Accuracy 55.0% (11 hit, 9 miss, across 20 underdog calls on 227 resolved calls).
- Winner Accuracy 70.0% 159 68
- Method Accuracy 39.9% 59 89
- Round AccuracyCalls the winner, not the round
- Underdog Accuracy 55.0% 11 9
Jimbo Ortega MMA
Current pick evidence
Picked: Roberto Soldić
Fight result: Roberto Soldić · Decision
Jimbo Ortega MMA selects Roberto Soldic in a winner-only call.
Track record: winner called in 38 of 56 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 67.9% (38 hit, 18 miss, across 56 resolved calls). Method Accuracy 62.1% (18 hit, 11 miss, across 29 method-scored calls on 56 resolved calls). Round Accuracy 50.0% (1 hit, 1 miss, across 2 round-scored calls on 56 resolved calls). Underdog Accuracy 50.0% (4 hit, 4 miss, across 8 underdog calls on 56 resolved calls).
- Winner Accuracy 67.9% 38 18
- Method Accuracy 62.1% 18 11
- Round Accuracy 50.0% 1 1
- Underdog Accuracy 50.0% 4 4
Michael Chiesa
Current pick evidence
Picked: Roberto Soldić
Fight result: Roberto Soldić · Decision
Chiesa picks Soldic in a matchup he expects to revolve around landing powerful shots. He favors Soldic's ability to combine his left hand and left kick, while noting Williams can counter the kick-first combination or excessive pressure.
“I am going with Roberto Soldich.”
Track record: winner called in 50 of 75 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 66.7% (50 hit, 25 miss, across 75 resolved calls). Method Accuracy 40.0% (2 hit, 3 miss, across 5 method-scored calls on 75 resolved calls). Round Accuracy: No round picks. Underdog Accuracy 16.7% (2 hit, 10 miss, across 12 underdog calls on 75 resolved calls).
- Winner Accuracy 66.7% 50 25
- Method Accuracy 40.0% 2 3
- Round AccuracyCalls the winner, not the round
- Underdog Accuracy 16.7% 2 10
Matt
Current pick evidence
Picked: Roberto Soldić
Fight result: Roberto Soldić · Decision
Leans toward UFC newcomer Soldic with little confidence and declines to bet; his possible decision is tentative.
Track record: winner called in 14 of 21 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 66.7% (14 hit, 7 miss, across 21 resolved calls). Method Accuracy 66.7% (6 hit, 3 miss, across 9 method-scored calls on 21 resolved calls). Round Accuracy 40.0% (2 hit, 3 miss, across 5 round-scored calls on 21 resolved calls). Underdog Accuracy: No underdog calls with a known pre-fight price.
- Winner Accuracy 66.7% 14 7
- Method Accuracy 66.7% 6 3
- Round Accuracy 40.0% 2 3
- Underdog AccuracyNo underdog calls with a known pre-fight price
The MMA Guru
Current pick evidence
Picked: Roberto Soldić · KO/TKO
Fight result: Roberto Soldić · Decision
Favors Soldic’s power, deceptive combinations and counters to stop Williams. Calls it a risky matchup because Williams can also knock him out, particularly with Soldic returning to welterweight.
Track record: winner called in 213 of 322 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 66.1% (213 hit, 109 miss, across 322 resolved calls). Method Accuracy 53.4% (62 hit, 54 miss, across 116 method-scored calls on 322 resolved calls). Round Accuracy 35.9% (14 hit, 25 miss, across 39 round-scored calls on 322 resolved calls). Underdog Accuracy 47.4% (18 hit, 20 miss, across 38 underdog calls on 322 resolved calls).
- Winner Accuracy 66.1% 213 109
- Method Accuracy 53.4% 62 54
- Round Accuracy 35.9% 14 25
- Underdog Accuracy 47.4% 18 20
JakeGerberMMA
Current pick evidence
Picked: Roberto Soldić · KO/TKO
Fight result: Roberto Soldić · Decision
Jake picks Roberto Soldic by knockout, expecting him to time Khaos Williams’s looping punches with a straight left down the middle and finish early. No particular round is stated.
“where I think Roberto's going to be able to time him with a good straight left hand down the middle and put him away early in this fight.”
Track record: winner called in 101 of 154 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 65.6% (101 hit, 53 miss, across 154 resolved calls). Method Accuracy 60.0% (39 hit, 26 miss, across 65 method-scored calls on 154 resolved calls). Round Accuracy 35.7% (5 hit, 9 miss, across 14 round-scored calls on 154 resolved calls). Underdog Accuracy 33.3% (4 hit, 8 miss, across 12 underdog calls on 154 resolved calls).
- Winner Accuracy 65.6% 101 53
- Method Accuracy 60.0% 39 26
- Round Accuracy 35.7% 5 9
- Underdog Accuracy 33.3% 4 8
Brent Brookhouse
Current pick evidence
Picked: Roberto Soldić · KO/TKO · Round 2
Fight result: Roberto Soldić · Decision
Brent Brookhouse picks Roberto Soldic to win by second-round KO.
Track record: winner called in 28 of 43 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 65.1% (28 hit, 15 miss, across 43 resolved calls). Method Accuracy 36.4% (8 hit, 14 miss, across 22 method-scored calls on 43 resolved calls). Round Accuracy 22.2% (2 hit, 7 miss, across 9 round-scored calls on 43 resolved calls). Underdog Accuracy 37.5% (3 hit, 5 miss, across 8 underdog calls on 43 resolved calls).
- Winner Accuracy 65.1% 28 15
- Method Accuracy 36.4% 8 14
- Round Accuracy 22.2% 2 7
- Underdog Accuracy 37.5% 3 5
Mate Bersenadze
Current pick evidence
Picked: Roberto Soldić · KO/TKO
Fight result: Roberto Soldić · Decision
Mate Bersenadze picks Roberto Soldic by KO/TKO, per his UFC 332 preview.
Track record: winner called in 33 of 52 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 63.5% (33 hit, 19 miss, across 52 resolved calls). Method Accuracy 51.5% (17 hit, 16 miss, across 33 method-scored calls on 52 resolved calls). Round Accuracy 100.0% (1 hit, 0 miss, across 1 round-scored calls on 52 resolved calls). Underdog Accuracy 33.3% (2 hit, 4 miss, across 6 underdog calls on 52 resolved calls).
- Winner Accuracy 63.5% 33 19
- Method Accuracy 51.5% 17 16
- Round Accuracy 100.0% 1
- Underdog Accuracy 33.3% 2 4
MMA JOEY
Current pick evidence
Picked: Roberto Soldić
Fight result: Roberto Soldić · Decision
MMA JOEY selects Roberto Soldic.
Track record: winner called in 78 of 125 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 62.4% (78 hit, 47 miss, across 125 resolved calls). Method Accuracy 46.6% (27 hit, 31 miss, across 58 method-scored calls on 125 resolved calls). Round Accuracy 28.1% (9 hit, 23 miss, across 32 round-scored calls on 125 resolved calls). Underdog Accuracy 33.3% (7 hit, 14 miss, across 21 underdog calls on 125 resolved calls).
- Winner Accuracy 62.4% 78 47
- Method Accuracy 46.6% 27 31
- Round Accuracy 28.1% 9 23
- Underdog Accuracy 33.3% 7 14
HopperMMA
Current pick evidence
Picked: Roberto Soldić · KO/TKO · Round 1
Fight result: Roberto Soldić · Decision
HopperoMMA selects Roberto Soldic by ko/tko in round 1.
Track record: winner called in 92 of 148 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 62.2% (92 hit, 56 miss, across 148 resolved calls). Method Accuracy 60.8% (45 hit, 29 miss, across 74 method-scored calls on 148 resolved calls). Round Accuracy 48.8% (20 hit, 21 miss, across 41 round-scored calls on 148 resolved calls). Underdog Accuracy 26.9% (7 hit, 19 miss, across 26 underdog calls on 148 resolved calls).
- Winner Accuracy 62.2% 92 56
- Method Accuracy 60.8% 45 29
- Round Accuracy 48.8% 20 21
- Underdog Accuracy 26.9% 7 19
Michael Bisping
Current pick evidence
Picked: Roberto Soldić
Fight result: Roberto Soldić · Decision
Bisping picks Soldic because he considers his approach more well-rounded. He still sees a knockout threat from Williams and notes Soldic's previous knockout defeats.
“anyway, I do have Soldic winning that fight.”
Track record: winner called in 24 of 39 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 61.5% (24 hit, 15 miss, across 39 resolved calls). Method Accuracy 33.3% (2 hit, 4 miss, across 6 method-scored calls on 39 resolved calls). Round Accuracy: No qualifying picks. Underdog Accuracy 28.6% (2 hit, 5 miss, across 7 underdog calls on 39 resolved calls).
- Winner Accuracy 61.5% 24 15
- Method Accuracy 33.3% 2 4
- Round AccuracyNamed rounds — none on a correct call yet
- Underdog Accuracy 28.6% 2 5
James Lynch
Current pick evidence
Picked: Roberto Soldić · KO/TKO · Round 3
Fight result: Roberto Soldić · Decision
Lynch predicts a third-round knockout for Soldic while allowing that the fight could reach the scorecards.
Track record: winner called in 36 of 59 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 61.0% (36 hit, 23 miss, across 59 resolved calls). Method Accuracy 45.0% (9 hit, 11 miss, across 20 method-scored calls on 59 resolved calls). Round Accuracy 0.0% (0 hit, 5 miss, across 5 round-scored calls on 59 resolved calls). Underdog Accuracy 60.0% (3 hit, 2 miss, across 5 underdog calls on 59 resolved calls).
- Winner Accuracy 61.0% 36 23
- Method Accuracy 45.0% 9 11
- Round Accuracy 0.0% 5
- Underdog Accuracy 60.0% 3 2
KingofCrackdown5095
Current pick evidence
Picked: Roberto Soldić · KO/TKO · Round 1
Fight result: Roberto Soldić · Decision
KingofCrackdown5095 picks Roberto Soldic by first-round TKO.
Track record: winner called in 37 of 63 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 58.7% (37 hit, 26 miss, across 63 resolved calls). Method Accuracy 65.6% (21 hit, 11 miss, across 32 method-scored calls on 63 resolved calls). Round Accuracy 42.1% (8 hit, 11 miss, across 19 round-scored calls on 63 resolved calls). Underdog Accuracy 42.9% (3 hit, 4 miss, across 7 underdog calls on 63 resolved calls).
- Winner Accuracy 58.7% 37 26
- Method Accuracy 65.6% 21 11
- Round Accuracy 42.1% 8 11
- Underdog Accuracy 42.9% 3 4
The Octagon Oracle
Current pick evidence
Picked: Roberto Soldić · KO/TKO
Fight result: Roberto Soldić · Decision
Picks Soldic by TKO because Williams offers little defense, while remaining cautious about Soldic’s recent form.
Track record: winner called in 7 of 12 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 58.3% (7 hit, 5 miss, across 12 resolved calls). Method Accuracy 85.7% (6 hit, 1 miss, across 7 method-scored calls on 12 resolved calls). Round Accuracy: No round picks. Underdog Accuracy: No underdog calls with a known pre-fight price.
- Winner Accuracy 58.3% 7 5
- Method Accuracy 85.7% 6 1
- Round AccuracyCalls the winner, not the round
- Underdog AccuracyNo underdog calls with a known pre-fight price
Artem MMA
Current pick evidence
Picked: Roberto Soldić · KO/TKO
Fight result: Roberto Soldić · Decision
Expects Soldic’s forward pressure and left hook to produce the knockout, while recognizing Williams’s danger in a striking fight. Dislikes Soldic’s price and worries about his defensive responsibility and reliance on the same hook.
Track record: winner called in 55 of 95 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 57.9% (55 hit, 40 miss, across 95 resolved calls). Method Accuracy 63.8% (30 hit, 17 miss, across 47 method-scored calls on 95 resolved calls). Round Accuracy 60.0% (6 hit, 4 miss, across 10 round-scored calls on 95 resolved calls). Underdog Accuracy 23.5% (4 hit, 13 miss, across 17 underdog calls on 95 resolved calls).
- Winner Accuracy 57.9% 55 40
- Method Accuracy 63.8% 30 17
- Round Accuracy 60.0% 6 4
- Underdog Accuracy 23.5% 4 13
BeewolfMMA
Current pick evidence
Picked: Roberto Soldić · Dec
Fight result: Roberto Soldić · Decision
Favors Soldic while acknowledging Williams could score an upset. Chooses a decision, allowing that Soldic may prove less dangerous than he expects.
Track record: winner called in 13 of 23 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 56.5% (13 hit, 10 miss, across 23 resolved calls). Method Accuracy 100.0% (7 hit, 0 miss, across 7 method-scored calls on 23 resolved calls). Round Accuracy 83.3% (5 hit, 1 miss, across 6 round-scored calls on 23 resolved calls). Underdog Accuracy: No underdog calls with a known pre-fight price.
- Winner Accuracy 56.5% 13 10
- Method Accuracy 100.0% 7
- Round Accuracy 83.3% 5 1
- Underdog AccuracyNo underdog calls with a known pre-fight price
Jon Litterine
Current pick evidence
Picked: Roberto Soldić
Fight result: Roberto Soldić · Decision
Says UFC leadership wants to showcase its new signing and calls this favorable matchmaking.
Track record: winner called in 70 of 124 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 56.5% (70 hit, 54 miss, across 124 resolved calls). Method Accuracy: No qualifying picks. Round Accuracy: No round picks. Underdog Accuracy 28.0% (7 hit, 18 miss, across 25 underdog calls on 124 resolved calls).
- Winner Accuracy 56.5% 70 54
- Method AccuracyNamed methods — none on a correct call yet
- Round AccuracyCalls the winner, not the round
- Underdog Accuracy 28.0% 7 18
Fight Productions
Current pick evidence
Picked: Roberto Soldić · KO/TKO · Round 1
Fight result: Roberto Soldić · Decision
Fight Productions selects Roberto Soldic by ko/tko in round 1.
Track record: winner called in 37 of 66 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 56.1% (37 hit, 29 miss, across 66 resolved calls). Method Accuracy 75.7% (28 hit, 9 miss, across 37 method-scored calls on 66 resolved calls). Round Accuracy 41.7% (10 hit, 14 miss, across 24 round-scored calls on 66 resolved calls). Underdog Accuracy 25.0% (2 hit, 6 miss, across 8 underdog calls on 66 resolved calls).
- Winner Accuracy 56.1% 37 29
- Method Accuracy 75.7% 28 9
- Round Accuracy 41.7% 10 14
- Underdog Accuracy 25.0% 2 6
Brian Campbell
Current pick evidence
Picked: Roberto Soldić · KO/TKO · Round 1
Fight result: Roberto Soldić · Decision
Brian Campbell picks Roberto Soldic to win by first-round KO.
Track record: winner called in 24 of 43 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 55.8% (24 hit, 19 miss, across 43 resolved calls). Method Accuracy 65.0% (13 hit, 7 miss, across 20 method-scored calls on 43 resolved calls). Round Accuracy 7.1% (1 hit, 13 miss, across 14 round-scored calls on 43 resolved calls). Underdog Accuracy 25.0% (3 hit, 9 miss, across 12 underdog calls on 43 resolved calls).
- Winner Accuracy 55.8% 24 19
- Method Accuracy 65.0% 13 7
- Round Accuracy 7.1% 1 13
- Underdog Accuracy 25.0% 3 9
Clenbat
Current pick evidence
Picked: Roberto Soldić
Fight result: Roberto Soldić · Decision
Clenbat selects Roberto Soldic in a winner-only call.
Track record: winner called in 27 of 49 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 55.1% (27 hit, 22 miss, across 49 resolved calls). Method Accuracy: No qualifying picks. Round Accuracy: No round picks. Underdog Accuracy 37.5% (3 hit, 5 miss, across 8 underdog calls on 49 resolved calls).
- Winner Accuracy 55.1% 27 22
- Method AccuracyNamed methods — none on a correct call yet
- Round AccuracyCalls the winner, not the round
- Underdog Accuracy 37.5% 3 5
Shakiel Mahjouri
Current pick evidence
Picked: Roberto Soldić · KO/TKO · Round 2
Fight result: Roberto Soldić · Decision
Shakiel Mahjouri picks Roberto Soldic to win by second-round KO.
Track record: winner called in 25 of 46 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 54.3% (25 hit, 21 miss, across 46 resolved calls). Method Accuracy 50.0% (10 hit, 10 miss, across 20 method-scored calls on 46 resolved calls). Round Accuracy 0.0% (0 hit, 9 miss, across 9 round-scored calls on 46 resolved calls). Underdog Accuracy 23.1% (3 hit, 10 miss, across 13 underdog calls on 46 resolved calls).
- Winner Accuracy 54.3% 25 21
- Method Accuracy 50.0% 10 10
- Round Accuracy 0.0% 9
- Underdog Accuracy 23.1% 3 10
Cole Shelton
Current pick evidence
Picked: Roberto Soldić · KO/TKO
Fight result: Roberto Soldić · Decision
Shelton calls Soldic the more technical striker and expects him to pick Williams apart; he says Soldic will likely get a TKO in the first or second round.
Track record: winner called in 62 of 116 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 53.4% (62 hit, 54 miss, across 116 resolved calls). Method Accuracy 87.5% (7 hit, 1 miss, across 8 method-scored calls on 116 resolved calls). Round Accuracy: No qualifying picks. Underdog Accuracy 16.7% (3 hit, 15 miss, across 18 underdog calls on 116 resolved calls).
- Winner Accuracy 53.4% 62 54
- Method Accuracy 87.5% 7 1
- Round AccuracyNamed rounds — none on a correct call yet
- Underdog Accuracy 16.7% 3 15
The MMA Yuda
Current pick evidence
Picked: Roberto Soldić
Fight result: Roberto Soldić · Decision
The MMA Yuda selects Roberto Soldic.
Track record: winner called in 30 of 58 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 51.7% (30 hit, 28 miss, across 58 resolved calls). Method Accuracy 0.0% (0 hit, 1 miss, across 1 method-scored calls on 58 resolved calls). Round Accuracy: No qualifying picks. Underdog Accuracy 40.0% (4 hit, 6 miss, across 10 underdog calls on 58 resolved calls).
- Winner Accuracy 51.7% 30 28
- Method Accuracy 0.0% 1
- Round AccuracyNamed rounds — none on a correct call yet
- Underdog Accuracy 40.0% 4 6
Greedo Plays MMA
Current pick evidence
Picked: Roberto Soldić · KO/TKO · Round 1
Fight result: Roberto Soldić · Decision
Greedo Plays MMA selects Roberto Soldic by ko/tko in round 1.
Track record: winner called in 37 of 72 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 51.4% (37 hit, 35 miss, across 72 resolved calls). Method Accuracy 63.3% (19 hit, 11 miss, across 30 method-scored calls on 72 resolved calls). Round Accuracy 57.1% (8 hit, 6 miss, across 14 round-scored calls on 72 resolved calls). Underdog Accuracy 23.1% (3 hit, 10 miss, across 13 underdog calls on 72 resolved calls).
- Winner Accuracy 51.4% 37 35
- Method Accuracy 63.3% 19 11
- Round Accuracy 57.1% 8 6
- Underdog Accuracy 23.1% 3 10
Walk The Line MMA
Current pick evidence
Picked: Roberto Soldić · KO/TKO
Fight result: Roberto Soldić · Decision
Walk The Line MMA selects Roberto Soldic by ko/tko.
Track record: winner called in 27 of 54 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 50.0% (27 hit, 27 miss, across 54 resolved calls). Method Accuracy 57.9% (11 hit, 8 miss, across 19 method-scored calls on 54 resolved calls). Round Accuracy 40.0% (2 hit, 3 miss, across 5 round-scored calls on 54 resolved calls). Underdog Accuracy 12.5% (1 hit, 7 miss, across 8 underdog calls on 54 resolved calls).
- Winner Accuracy 50.0% 27 27
- Method Accuracy 57.9% 11 8
- Round Accuracy 40.0% 2 3
- Underdog Accuracy 12.5% 1 7
Vinny
Current pick evidence
Picked: Roberto Soldić · Sub · Round 1
Fight result: Roberto Soldić · Decision
Names Soldic by first-round submission in his final prediction recap.
Track record: winner called in 6 of 12 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 50.0% (6 hit, 6 miss, across 12 resolved calls). Method Accuracy 16.7% (1 hit, 5 miss, across 6 method-scored calls on 12 resolved calls). Round Accuracy 0.0% (0 hit, 4 miss, across 4 round-scored calls on 12 resolved calls). Underdog Accuracy: No underdog calls with a known pre-fight price.
- Winner Accuracy 50.0% 6 6
- Method Accuracy 16.7% 1 5
- Round Accuracy 0.0% 4
- Underdog AccuracyNo underdog calls with a known pre-fight price
Brandon Wise
Current pick evidence
Picked: Roberto Soldić · KO/TKO · Round 1
Fight result: Roberto Soldić · Decision
Brandon Wise picks Roberto Soldic to win by first-round KO.
Track record: winner called in 21 of 43 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 48.8% (21 hit, 22 miss, across 43 resolved calls). Method Accuracy 40.0% (6 hit, 9 miss, across 15 method-scored calls on 43 resolved calls). Round Accuracy 12.5% (1 hit, 7 miss, across 8 round-scored calls on 43 resolved calls). Underdog Accuracy 8.3% (1 hit, 11 miss, across 12 underdog calls on 43 resolved calls).
- Winner Accuracy 48.8% 21 22
- Method Accuracy 40.0% 6 9
- Round Accuracy 12.5% 1 7
- Underdog Accuracy 8.3% 1 11
mmadbm
Current pick evidence
Picked: Roberto Soldić · Dec
Fight result: Roberto Soldić · Decision
Picks Soldic by decision for his more technical, tricky kickboxing, footwork and volume, which he expects to frustrate Williams. He acknowledges Williams’s power and durability and does not expect Soldic to knock him out.
Track record: winner called in 20 of 41 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 48.8% (20 hit, 21 miss, across 41 resolved calls). Method Accuracy 85.7% (12 hit, 2 miss, across 14 method-scored calls on 41 resolved calls). Round Accuracy 100.0% (2 hit, 0 miss, across 2 round-scored calls on 41 resolved calls). Underdog Accuracy 14.3% (1 hit, 6 miss, across 7 underdog calls on 41 resolved calls).
- Winner Accuracy 48.8% 20 21
- Method Accuracy 85.7% 12 2
- Round Accuracy 100.0% 2
- Underdog Accuracy 14.3% 1 6
Brandon K
Current pick evidence
Picked: Roberto Soldić
Fight result: Roberto Soldić · Decision
Brandon K selects Roberto Soldic in a winner-only call.
Track record: winner called in 20 of 45 resolved picks. How winner calls are counted
Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology
Winner Accuracy 44.4% (20 hit, 25 miss, across 45 resolved calls). Method Accuracy 42.9% (6 hit, 8 miss, across 14 method-scored calls on 45 resolved calls). Round Accuracy 0.0% (0 hit, 5 miss, across 5 round-scored calls on 45 resolved calls). Underdog Accuracy 25.0% (3 hit, 9 miss, across 12 underdog calls on 45 resolved calls).
- Winner Accuracy 44.4% 20 25
- Method Accuracy 42.9% 6 8
- Round Accuracy 0.0% 5
- Underdog Accuracy 25.0% 3 9
Analyst picks: Hank Hit; Bedtime MMA Hit; FightIQ Hit; Jimbo Ortega MMA Hit; Michael Chiesa Hit; Matt Hit; The MMA Guru Hit; JakeGerberMMA Hit; Brent Brookhouse Hit; Fite Feed Miss; Mate Bersenadze Hit; MMA JOEY Hit; HopperMMA Hit; Michael Bisping Hit; James Lynch Hit; KingofCrackdown5095 Hit; Kunath Miss; The Octagon Oracle Hit; Angelo Bodetti Miss; Artem MMA Hit; BeewolfMMA Hit; Jon Litterine Hit; Fight Productions Hit; Brian Campbell Hit; Clenbat Hit; The Finz Chats Miss; Shakiel Mahjouri Hit; Chris Schweppe Miss; Cole Shelton Hit; D.Rose Miss; The MMA Yuda Hit; Greedo Plays MMA Hit; Walk The Line MMA Hit; Vinny Hit; Brandon Wise Hit; mmadbm Hit; Gerardo Rivas Miss; Brandon K Hit; Timothy Wheaton Miss; Chris Cross Miss; Carlos Cano Miss.
31 of 41 nailed it.
Chart: selected analyst picks, not a win probability. Pill badge: Winner hit rate (total scored picks before this event).
| Expand row |
|---|
The experts above are a lens, not credentials we conferred — analyst, fighter or betting desk.
Results
Each agent’s latest pre-fight call vs result; forecast dates may differ. Market: sportsbook snapshot or historic market reconstruction.
Actual Soldić · Decision · R3
Closest probability Gemini put 70% on Soldić.
42%
Williams
58%
Soldić
PickSoldić · KO/TKO · R2ActualSoldić · Decision · R3
WinnerHitMethodMissRoundNot applicable — decisions have no finishing round
55%
Williams
45%
Soldić
PickWilliams · KO/TKO · R2ActualSoldić · Decision · R3
WinnerMissMethodNot applicable — the winner call missedRoundNot applicable — the winner call missed
30%
Williams
70%
Soldić
PickSoldić · KO/TKO · R2ActualSoldić · Decision · R3
WinnerHitMethodMissRoundNot applicable — decisions have no finishing roundAI Predictions — latest pre-fight calls
Frozen final publication identity; the calls below retain each agent’s own publication.AI Predictions
Each agent’s latest pre-fight forecast. Dates are shown per agent.
ChatGPT
63 of 108 winner picks correct · 58% hit rate
Pick Soldić
Most likely: Soldić by KO/TKO, about 32 in 100
Win chance: Williams 42%, Soldić 58%.
Confidence 6 of 10 · Medium
Claude
61 of 101 winner picks correct · 60% hit rate
Pick Williams
Most likely: a tie between Williams by KO/TKO and Soldić by KO/TKO, about 30 in 100 each
Win chance: Williams 55%, Soldić 45%.
Confidence 6 of 10 · Medium
Gemini
68 of 108 winner picks correct · 63% hit rate
Pick Soldić
Most likely: Soldić by KO/TKO, about 45 in 100
Win chance: Williams 30%, Soldić 70%.
Confidence 7 of 10 · High
1 of 3 models pick Williams; 2 of 3 models pick Soldić.
Questions
The result 7 questions
Who wins, and how likely?
ChatGPT
Soldić: 58% (about 58 in 100 fights). Williams: 42%.
Claude
Williams: 55% (about 55 in 100 fights). Soldić: 45%.
Gemini
Soldić: 70% (about 70 in 100 fights). Williams: 30%.
What is the single most likely outcome?
ChatGPT
Soldić by KO/TKO: 32% (about 32 in 100).
Claude
A tie: Williams by KO/TKO and Soldić by KO/TKO, 30% each (about 30 in 100 each).
Gemini
Soldić by KO/TKO: 45% (about 45 in 100).
What are the three most likely outcomes, and why?
ChatGPT
1. Soldić by KO/TKO (32%); 2. Williams by KO/TKO (26%); 3. Soldić by decision (24%)
Claude
1. Williams by KO/TKO (30%); 1. Soldić by KO/TKO (30%); 3. Williams by decision (20%)
Gemini
1. Soldić by KO/TKO (45%); 2. Soldić by decision (23%); 3. Williams by KO/TKO (19%)
How confident is the model?
ChatGPT
6 of 10, based on Soldić's 58% win chance.
Claude
6 of 10, based on Williams's 55% win chance.
Gemini
7 of 10, based on Soldić's 70% win chance.
Does it end early or go to the judges?
ChatGPT
Finish (KO/TKO or submission): 61%. Decision: 39%.
Claude
Finish (KO/TKO or submission): 68%. Decision: 32%.
Gemini
Finish (KO/TKO or submission): 67%. Decision: 33%.
How does Williams win?
ChatGPT
Williams wins 42%: KO/TKO 26%, submission 1%, decision 15%.
Claude
Williams wins 55%: KO/TKO 30%, submission 5%, decision 20%.
Gemini
Williams wins 30%: KO/TKO 19%, submission 1%, decision 10%.
How does Soldić win?
ChatGPT
Soldić wins 58%: KO/TKO 32%, submission 2%, decision 24%.
Claude
Soldić wins 45%: KO/TKO 30%, submission 3%, decision 12%.
Gemini
Soldić wins 70%: KO/TKO 45%, submission 2%, decision 23%.
Compared with others 1 question
Do the models agree?
All models
The models split 2–1 (ChatGPT: Soldić, Claude: Williams, Gemini: Soldić).
After the fight 2 questions
What happened vs what the model said?
ChatGPT
Result: Soldić by decision, the model's number 3 outcome. Its most likely outcome was Soldić by KO/TKO (32%).
Claude
Result: Soldić by decision, the model's number 4 outcome. Its most likely outcomes were Williams by KO/TKO and Soldić by KO/TKO (30% each).
Gemini
Result: Soldić by decision, the model's number 2 outcome. Its most likely outcome was Soldić by KO/TKO (45%).
How much chance did it give the actual result?
ChatGPT
24% (about 24 in 100).
Claude
12% (about 12 in 100).
Gemini
23% (about 23 in 100).
More questions (17)
The result 6 questions
KO/TKO vs submission vs decision overall
ChatGPT
KO/TKO 58%, submission 3%, decision 39%.
Claude
KO/TKO 60%, submission 8%, decision 32%.
Gemini
KO/TKO 64%, submission 3%, decision 33%.
Who is more likely to finish the other?
ChatGPT
Soldić: 34%, against 27% for Williams.
Claude
Williams: 35%, against 33% for Soldić.
Gemini
Soldić: 47%, against 20% for Williams.
Can Williams get the finish? Can Soldić?
ChatGPT
Williams: 27% (KO/TKO 26%, submission 1%). Soldić: 34% (KO/TKO 32%, submission 2%).
Claude
Williams: 35% (KO/TKO 30%, submission 5%). Soldić: 33% (KO/TKO 30%, submission 3%).
Gemini
Williams: 20% (KO/TKO 19%, submission 1%). Soldić: 47% (KO/TKO 45%, submission 2%).
Who is more likely to be knocked out, and who to be submitted?
ChatGPT
Williams is knocked out in 32% and submitted in 2%. Soldić is knocked out in 26% and submitted in 1%.
Claude
Williams is knocked out in 30% and submitted in 3%. Soldić is knocked out in 30% and submitted in 5%.
Gemini
Williams is knocked out in 45% and submitted in 2%. Soldić is knocked out in 19% and submitted in 1%.
How lopsided is this fight?
ChatGPT
A clear favourite: 58% vs 42%.
Claude
A clear favourite: 55% vs 45%.
Gemini
Lopsided: 70% vs 30%.
How big an upset would it be if the underdog wins?
ChatGPT
Williams wins 42% (about 1 in 2 fights): a modest upset.
Claude
Soldić wins 45% (about 1 in 2 fights): a modest upset.
Gemini
Williams wins 30% (about 1 in 3 fights): a big upset.
Timing 1 question
Chance it goes to a decision
ChatGPT
39%.
Claude
32%.
Gemini
33%.
What if 1 question
If it goes to the judges, who wins?
ChatGPT
If it goes to the judges: Williams 39%, Soldić 62%.
Claude
If it goes to the judges: Williams 63%, Soldić 38%.
Gemini
If it goes to the judges: Williams 30%, Soldić 70%.
Compared with others 3 questions
Where does this model differ from the others?
ChatGPT
Biggest difference: Soldić by decision, 24% here against 18% on average for the others.
Claude
Biggest difference: Soldić by decision, 12% here against 24% on average for the others.
How does it compare with analyst picks?
ChatGPT
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Soldić (58%).
Claude
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Williams (55%).
Gemini
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Soldić (70%).
Which model is most confident on Williams, and which on Soldić?
All models
On Williams: Claude (55%). On Soldić: Gemini (70%).
How sure 4 questions
When was this forecast made, and by which model version?
ChatGPT
On 27 Sep 2026, by gpt-6-astra.
Claude
On 27 Sep 2026, by claude-sonnet-5.
Gemini
On 29 Sep 2026, by a model version the provider did not report.
What can't the model know?
FightCard
Models research public information before the fight, such as records, styles, recent results and coverage. They cannot see inside training camps, injuries nobody has reported, or what happens on the night. A small chance is not no chance: outcomes the model rates at a few percent still happen, and big favourites lose sometimes.
How is "confidence" worked out?
FightCard
Confidence restates the favourite's win chance on a 10-step scale: the win chance in tens, rounded, so 55% is 6 of 10 and 95% or more is 10 of 10. 1 to 3 reads Low, 4 to 6 Medium and 7 to 10 High. A favourite usually has at least half the chance, so most picks show 5 or more. When the model has the fighters exactly even, there is no pick and no confidence level. It is not a separate judgement by the model.
What counts as a KO, a decision or a draw?
FightCard
KO/TKO includes referee, doctor and corner stoppages, and disqualifications. A decision includes a fight stopped early and scored on the judges' cards. A stoppage between rounds counts as a finish in the round that just ended. A draw and a no contest share one outcome.
After the fight 2 questions
Which model was closest?
All models
ChatGPT, which gave the actual result 24%.
Was the actual result in this model's top 3?
ChatGPT
Yes.
Claude
No.
Gemini
Yes.
ChatGPT
Pick
Soldić
Confidence 6 of 10 · Medium
Most likely: Soldić by KO/TKO, about 32 in 100
The model's predicted finish round: 2.
Win chance: Williams 42%, Soldić 58%.
Most likely outcomes
- Soldić by KO/TKO32%
- Williams by KO/TKO26%
- Soldić by decision24%
- KO/TKO: Williams 26%, Soldić 32%.
- Submission: Williams 1%, Soldić 2%.
- Decision: Williams 15%, Soldić 24%.
Questions
The result 7 questions
Who wins, and how likely?
ChatGPT
Soldić: 58% (about 58 in 100 fights). Williams: 42%.
Other models' answers
Claude
Williams: 55% (about 55 in 100 fights). Soldić: 45%.
Gemini
Soldić: 70% (about 70 in 100 fights). Williams: 30%.
What is the single most likely outcome?
ChatGPT
Soldić by KO/TKO: 32% (about 32 in 100).
Other models' answers
Claude
A tie: Williams by KO/TKO and Soldić by KO/TKO, 30% each (about 30 in 100 each).
Gemini
Soldić by KO/TKO: 45% (about 45 in 100).
What are the three most likely outcomes, and why?
ChatGPT
1. Soldić by KO/TKO (32%); 2. Williams by KO/TKO (26%); 3. Soldić by decision (24%)
Other models' answers
Claude
1. Williams by KO/TKO (30%); 1. Soldić by KO/TKO (30%); 3. Williams by decision (20%)
Gemini
1. Soldić by KO/TKO (45%); 2. Soldić by decision (23%); 3. Williams by KO/TKO (19%)
How confident is the model?
ChatGPT
6 of 10, based on Soldić's 58% win chance.
Other models' answers
Claude
6 of 10, based on Williams's 55% win chance.
Gemini
7 of 10, based on Soldić's 70% win chance.
Does it end early or go to the judges?
ChatGPT
Finish (KO/TKO or submission): 61%. Decision: 39%.
Other models' answers
Claude
Finish (KO/TKO or submission): 68%. Decision: 32%.
Gemini
Finish (KO/TKO or submission): 67%. Decision: 33%.
How does Williams win?
ChatGPT
Williams wins 42%: KO/TKO 26%, submission 1%, decision 15%.
Other models' answers
Claude
Williams wins 55%: KO/TKO 30%, submission 5%, decision 20%.
Gemini
Williams wins 30%: KO/TKO 19%, submission 1%, decision 10%.
How does Soldić win?
ChatGPT
Soldić wins 58%: KO/TKO 32%, submission 2%, decision 24%.
Other models' answers
Claude
Soldić wins 45%: KO/TKO 30%, submission 3%, decision 12%.
Gemini
Soldić wins 70%: KO/TKO 45%, submission 2%, decision 23%.
Compared with others 1 question
Do the models agree?
ChatGPT
The models split 2–1 (ChatGPT: Soldić, Claude: Williams, Gemini: Soldić).
After the fight 2 questions
What happened vs what the model said?
ChatGPT
Result: Soldić by decision, the model's number 3 outcome. Its most likely outcome was Soldić by KO/TKO (32%).
Other models' answers
Claude
Result: Soldić by decision, the model's number 4 outcome. Its most likely outcomes were Williams by KO/TKO and Soldić by KO/TKO (30% each).
Gemini
Result: Soldić by decision, the model's number 2 outcome. Its most likely outcome was Soldić by KO/TKO (45%).
How much chance did it give the actual result?
ChatGPT
24% (about 24 in 100).
Other models' answers
Claude
12% (about 12 in 100).
Gemini
23% (about 23 in 100).
More questions (17)
The result 6 questions
KO/TKO vs submission vs decision overall
ChatGPT
KO/TKO 58%, submission 3%, decision 39%.
Other models' answers
Claude
KO/TKO 60%, submission 8%, decision 32%.
Gemini
KO/TKO 64%, submission 3%, decision 33%.
Who is more likely to finish the other?
ChatGPT
Soldić: 34%, against 27% for Williams.
Other models' answers
Claude
Williams: 35%, against 33% for Soldić.
Gemini
Soldić: 47%, against 20% for Williams.
Can Williams get the finish? Can Soldić?
ChatGPT
Williams: 27% (KO/TKO 26%, submission 1%). Soldić: 34% (KO/TKO 32%, submission 2%).
Other models' answers
Claude
Williams: 35% (KO/TKO 30%, submission 5%). Soldić: 33% (KO/TKO 30%, submission 3%).
Gemini
Williams: 20% (KO/TKO 19%, submission 1%). Soldić: 47% (KO/TKO 45%, submission 2%).
Who is more likely to be knocked out, and who to be submitted?
ChatGPT
Williams is knocked out in 32% and submitted in 2%. Soldić is knocked out in 26% and submitted in 1%.
Other models' answers
Claude
Williams is knocked out in 30% and submitted in 3%. Soldić is knocked out in 30% and submitted in 5%.
Gemini
Williams is knocked out in 45% and submitted in 2%. Soldić is knocked out in 19% and submitted in 1%.
How lopsided is this fight?
ChatGPT
A clear favourite: 58% vs 42%.
Other models' answers
Claude
A clear favourite: 55% vs 45%.
Gemini
Lopsided: 70% vs 30%.
How big an upset would it be if the underdog wins?
ChatGPT
Williams wins 42% (about 1 in 2 fights): a modest upset.
Other models' answers
Claude
Soldić wins 45% (about 1 in 2 fights): a modest upset.
Gemini
Williams wins 30% (about 1 in 3 fights): a big upset.
Timing 1 question
Chance it goes to a decision
ChatGPT
39%.
Other models' answers
Claude
32%.
Gemini
33%.
What if 1 question
If it goes to the judges, who wins?
ChatGPT
If it goes to the judges: Williams 39%, Soldić 62%.
Other models' answers
Claude
If it goes to the judges: Williams 63%, Soldić 38%.
Gemini
If it goes to the judges: Williams 30%, Soldić 70%.
Compared with others 3 questions
Where does this model differ from the others?
ChatGPT
Biggest difference: Soldić by decision, 24% here against 18% on average for the others.
Other models' answers
Claude
Biggest difference: Soldić by decision, 12% here against 24% on average for the others.
How does it compare with analyst picks?
ChatGPT
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Soldić (58%).
Other models' answers
Claude
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Williams (55%).
Gemini
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Soldić (70%).
Which model is most confident on Williams, and which on Soldić?
ChatGPT
On Williams: Claude (55%). On Soldić: Gemini (70%).
How sure 4 questions
When was this forecast made, and by which model version?
ChatGPT
On 27 Sep 2026, by gpt-6-astra.
Other models' answers
Claude
On 27 Sep 2026, by claude-sonnet-5.
Gemini
On 29 Sep 2026, by a model version the provider did not report.
What can't the model know?
FightCard
Models research public information before the fight, such as records, styles, recent results and coverage. They cannot see inside training camps, injuries nobody has reported, or what happens on the night. A small chance is not no chance: outcomes the model rates at a few percent still happen, and big favourites lose sometimes.
How is "confidence" worked out?
FightCard
Confidence restates the favourite's win chance on a 10-step scale: the win chance in tens, rounded, so 55% is 6 of 10 and 95% or more is 10 of 10. 1 to 3 reads Low, 4 to 6 Medium and 7 to 10 High. A favourite usually has at least half the chance, so most picks show 5 or more. When the model has the fighters exactly even, there is no pick and no confidence level. It is not a separate judgement by the model.
What counts as a KO, a decision or a draw?
FightCard
KO/TKO includes referee, doctor and corner stoppages, and disqualifications. A decision includes a fight stopped early and scored on the judges' cards. A stoppage between rounds counts as a finish in the round that just ended. A draw and a no contest share one outcome.
After the fight 2 questions
Which model was closest?
ChatGPT
ChatGPT, which gave the actual result 24%.
Was the actual result in this model's top 3?
ChatGPT
Yes.
Other models' answers
Claude
No.
gpt-6-astra · 27 Sep63 of 108 winner picks correct · 58% hit rate
Claude
Pick
Williams
Confidence 6 of 10 · Medium
Most likely: a tie between Williams by KO/TKO and Soldić by KO/TKO, about 30 in 100 each
The model's predicted finish round: 2.
Win chance: Williams 55%, Soldić 45%.
Most likely outcomes
- Williams by KO/TKO, tied for number 130%
- Soldić by KO/TKO, tied for number 130%
- Williams by decision20%
- KO/TKO: Williams 30%, Soldić 30%.
- Submission: Williams 5%, Soldić 3%.
- Decision: Williams 20%, Soldić 12%.
Questions
The result 7 questions
Who wins, and how likely?
Claude
Williams: 55% (about 55 in 100 fights). Soldić: 45%.
Other models' answers
ChatGPT
Soldić: 58% (about 58 in 100 fights). Williams: 42%.
Gemini
Soldić: 70% (about 70 in 100 fights). Williams: 30%.
What is the single most likely outcome?
Claude
A tie: Williams by KO/TKO and Soldić by KO/TKO, 30% each (about 30 in 100 each).
Other models' answers
ChatGPT
Soldić by KO/TKO: 32% (about 32 in 100).
Gemini
Soldić by KO/TKO: 45% (about 45 in 100).
What are the three most likely outcomes, and why?
Claude
1. Williams by KO/TKO (30%); 1. Soldić by KO/TKO (30%); 3. Williams by decision (20%)
Other models' answers
ChatGPT
1. Soldić by KO/TKO (32%); 2. Williams by KO/TKO (26%); 3. Soldić by decision (24%)
Gemini
1. Soldić by KO/TKO (45%); 2. Soldić by decision (23%); 3. Williams by KO/TKO (19%)
How confident is the model?
Claude
6 of 10, based on Williams's 55% win chance.
Other models' answers
ChatGPT
6 of 10, based on Soldić's 58% win chance.
Gemini
7 of 10, based on Soldić's 70% win chance.
Does it end early or go to the judges?
Claude
Finish (KO/TKO or submission): 68%. Decision: 32%.
Other models' answers
ChatGPT
Finish (KO/TKO or submission): 61%. Decision: 39%.
Gemini
Finish (KO/TKO or submission): 67%. Decision: 33%.
How does Williams win?
Claude
Williams wins 55%: KO/TKO 30%, submission 5%, decision 20%.
Other models' answers
ChatGPT
Williams wins 42%: KO/TKO 26%, submission 1%, decision 15%.
Gemini
Williams wins 30%: KO/TKO 19%, submission 1%, decision 10%.
How does Soldić win?
Claude
Soldić wins 45%: KO/TKO 30%, submission 3%, decision 12%.
Other models' answers
ChatGPT
Soldić wins 58%: KO/TKO 32%, submission 2%, decision 24%.
Gemini
Soldić wins 70%: KO/TKO 45%, submission 2%, decision 23%.
Compared with others 1 question
Do the models agree?
Claude
The models split 2–1 (ChatGPT: Soldić, Claude: Williams, Gemini: Soldić).
After the fight 2 questions
What happened vs what the model said?
Claude
Result: Soldić by decision, the model's number 4 outcome. Its most likely outcomes were Williams by KO/TKO and Soldić by KO/TKO (30% each).
Other models' answers
ChatGPT
Result: Soldić by decision, the model's number 3 outcome. Its most likely outcome was Soldić by KO/TKO (32%).
Gemini
Result: Soldić by decision, the model's number 2 outcome. Its most likely outcome was Soldić by KO/TKO (45%).
How much chance did it give the actual result?
Claude
12% (about 12 in 100).
Other models' answers
ChatGPT
24% (about 24 in 100).
Gemini
23% (about 23 in 100).
More questions (17)
The result 6 questions
KO/TKO vs submission vs decision overall
Claude
KO/TKO 60%, submission 8%, decision 32%.
Other models' answers
ChatGPT
KO/TKO 58%, submission 3%, decision 39%.
Gemini
KO/TKO 64%, submission 3%, decision 33%.
Who is more likely to finish the other?
Claude
Williams: 35%, against 33% for Soldić.
Other models' answers
ChatGPT
Soldić: 34%, against 27% for Williams.
Gemini
Soldić: 47%, against 20% for Williams.
Can Williams get the finish? Can Soldić?
Claude
Williams: 35% (KO/TKO 30%, submission 5%). Soldić: 33% (KO/TKO 30%, submission 3%).
Other models' answers
ChatGPT
Williams: 27% (KO/TKO 26%, submission 1%). Soldić: 34% (KO/TKO 32%, submission 2%).
Gemini
Williams: 20% (KO/TKO 19%, submission 1%). Soldić: 47% (KO/TKO 45%, submission 2%).
Who is more likely to be knocked out, and who to be submitted?
Claude
Williams is knocked out in 30% and submitted in 3%. Soldić is knocked out in 30% and submitted in 5%.
Other models' answers
ChatGPT
Williams is knocked out in 32% and submitted in 2%. Soldić is knocked out in 26% and submitted in 1%.
Gemini
Williams is knocked out in 45% and submitted in 2%. Soldić is knocked out in 19% and submitted in 1%.
How lopsided is this fight?
Claude
A clear favourite: 55% vs 45%.
Other models' answers
ChatGPT
A clear favourite: 58% vs 42%.
Gemini
Lopsided: 70% vs 30%.
How big an upset would it be if the underdog wins?
Claude
Soldić wins 45% (about 1 in 2 fights): a modest upset.
Other models' answers
ChatGPT
Williams wins 42% (about 1 in 2 fights): a modest upset.
Gemini
Williams wins 30% (about 1 in 3 fights): a big upset.
Timing 1 question
Chance it goes to a decision
Claude
32%.
Other models' answers
ChatGPT
39%.
Gemini
33%.
What if 1 question
If it goes to the judges, who wins?
Claude
If it goes to the judges: Williams 63%, Soldić 38%.
Other models' answers
ChatGPT
If it goes to the judges: Williams 39%, Soldić 62%.
Gemini
If it goes to the judges: Williams 30%, Soldić 70%.
Compared with others 3 questions
Where does this model differ from the others?
Claude
Biggest difference: Soldić by decision, 12% here against 24% on average for the others.
Other models' answers
ChatGPT
Biggest difference: Soldić by decision, 24% here against 18% on average for the others.
How does it compare with analyst picks?
Claude
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Williams (55%).
Other models' answers
ChatGPT
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Soldić (58%).
Gemini
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Soldić (70%).
Which model is most confident on Williams, and which on Soldić?
Claude
On Williams: Claude (55%). On Soldić: Gemini (70%).
How sure 4 questions
When was this forecast made, and by which model version?
Claude
On 27 Sep 2026, by claude-sonnet-5.
Other models' answers
ChatGPT
On 27 Sep 2026, by gpt-6-astra.
Gemini
On 29 Sep 2026, by a model version the provider did not report.
What can't the model know?
FightCard
Models research public information before the fight, such as records, styles, recent results and coverage. They cannot see inside training camps, injuries nobody has reported, or what happens on the night. A small chance is not no chance: outcomes the model rates at a few percent still happen, and big favourites lose sometimes.
How is "confidence" worked out?
FightCard
Confidence restates the favourite's win chance on a 10-step scale: the win chance in tens, rounded, so 55% is 6 of 10 and 95% or more is 10 of 10. 1 to 3 reads Low, 4 to 6 Medium and 7 to 10 High. A favourite usually has at least half the chance, so most picks show 5 or more. When the model has the fighters exactly even, there is no pick and no confidence level. It is not a separate judgement by the model.
What counts as a KO, a decision or a draw?
FightCard
KO/TKO includes referee, doctor and corner stoppages, and disqualifications. A decision includes a fight stopped early and scored on the judges' cards. A stoppage between rounds counts as a finish in the round that just ended. A draw and a no contest share one outcome.
After the fight 2 questions
Which model was closest?
Claude
ChatGPT, which gave the actual result 24%.
Was the actual result in this model's top 3?
Claude
No.
Other models' answers
ChatGPT
Yes.
Gemini
Yes.
claude-sonnet-5 · 27 Sep61 of 101 winner picks correct · 60% hit rate
Gemini
Pick
Soldić
Confidence 7 of 10 · High
Most likely: Soldić by KO/TKO, about 45 in 100
The model's predicted finish round: 2.
Win chance: Williams 30%, Soldić 70%.
Most likely outcomes
- Soldić by KO/TKO45%
- Soldić by decision23%
- Williams by KO/TKO19%
- KO/TKO: Williams 19%, Soldić 45%.
- Submission: Williams 1%, Soldić 2%.
- Decision: Williams 10%, Soldić 23%.
Questions
The result 7 questions
Who wins, and how likely?
Gemini
Soldić: 70% (about 70 in 100 fights). Williams: 30%.
Other models' answers
ChatGPT
Soldić: 58% (about 58 in 100 fights). Williams: 42%.
Claude
Williams: 55% (about 55 in 100 fights). Soldić: 45%.
What is the single most likely outcome?
Gemini
Soldić by KO/TKO: 45% (about 45 in 100).
Other models' answers
ChatGPT
Soldić by KO/TKO: 32% (about 32 in 100).
Claude
A tie: Williams by KO/TKO and Soldić by KO/TKO, 30% each (about 30 in 100 each).
What are the three most likely outcomes, and why?
Gemini
1. Soldić by KO/TKO (45%); 2. Soldić by decision (23%); 3. Williams by KO/TKO (19%)
Other models' answers
ChatGPT
1. Soldić by KO/TKO (32%); 2. Williams by KO/TKO (26%); 3. Soldić by decision (24%)
Claude
1. Williams by KO/TKO (30%); 1. Soldić by KO/TKO (30%); 3. Williams by decision (20%)
How confident is the model?
Gemini
7 of 10, based on Soldić's 70% win chance.
Other models' answers
ChatGPT
6 of 10, based on Soldić's 58% win chance.
Claude
6 of 10, based on Williams's 55% win chance.
Does it end early or go to the judges?
Gemini
Finish (KO/TKO or submission): 67%. Decision: 33%.
Other models' answers
ChatGPT
Finish (KO/TKO or submission): 61%. Decision: 39%.
Claude
Finish (KO/TKO or submission): 68%. Decision: 32%.
How does Williams win?
Gemini
Williams wins 30%: KO/TKO 19%, submission 1%, decision 10%.
Other models' answers
ChatGPT
Williams wins 42%: KO/TKO 26%, submission 1%, decision 15%.
Claude
Williams wins 55%: KO/TKO 30%, submission 5%, decision 20%.
How does Soldić win?
Gemini
Soldić wins 70%: KO/TKO 45%, submission 2%, decision 23%.
Other models' answers
ChatGPT
Soldić wins 58%: KO/TKO 32%, submission 2%, decision 24%.
Claude
Soldić wins 45%: KO/TKO 30%, submission 3%, decision 12%.
Compared with others 1 question
Do the models agree?
Gemini
The models split 2–1 (ChatGPT: Soldić, Claude: Williams, Gemini: Soldić).
After the fight 2 questions
What happened vs what the model said?
Gemini
Result: Soldić by decision, the model's number 2 outcome. Its most likely outcome was Soldić by KO/TKO (45%).
Other models' answers
ChatGPT
Result: Soldić by decision, the model's number 3 outcome. Its most likely outcome was Soldić by KO/TKO (32%).
Claude
Result: Soldić by decision, the model's number 4 outcome. Its most likely outcomes were Williams by KO/TKO and Soldić by KO/TKO (30% each).
How much chance did it give the actual result?
Gemini
23% (about 23 in 100).
Other models' answers
ChatGPT
24% (about 24 in 100).
Claude
12% (about 12 in 100).
More questions (16)
The result 6 questions
KO/TKO vs submission vs decision overall
Gemini
KO/TKO 64%, submission 3%, decision 33%.
Other models' answers
ChatGPT
KO/TKO 58%, submission 3%, decision 39%.
Claude
KO/TKO 60%, submission 8%, decision 32%.
Who is more likely to finish the other?
Gemini
Soldić: 47%, against 20% for Williams.
Other models' answers
ChatGPT
Soldić: 34%, against 27% for Williams.
Claude
Williams: 35%, against 33% for Soldić.
Can Williams get the finish? Can Soldić?
Gemini
Williams: 20% (KO/TKO 19%, submission 1%). Soldić: 47% (KO/TKO 45%, submission 2%).
Other models' answers
ChatGPT
Williams: 27% (KO/TKO 26%, submission 1%). Soldić: 34% (KO/TKO 32%, submission 2%).
Claude
Williams: 35% (KO/TKO 30%, submission 5%). Soldić: 33% (KO/TKO 30%, submission 3%).
Who is more likely to be knocked out, and who to be submitted?
Gemini
Williams is knocked out in 45% and submitted in 2%. Soldić is knocked out in 19% and submitted in 1%.
Other models' answers
ChatGPT
Williams is knocked out in 32% and submitted in 2%. Soldić is knocked out in 26% and submitted in 1%.
Claude
Williams is knocked out in 30% and submitted in 3%. Soldić is knocked out in 30% and submitted in 5%.
How lopsided is this fight?
Gemini
Lopsided: 70% vs 30%.
Other models' answers
ChatGPT
A clear favourite: 58% vs 42%.
Claude
A clear favourite: 55% vs 45%.
How big an upset would it be if the underdog wins?
Gemini
Williams wins 30% (about 1 in 3 fights): a big upset.
Other models' answers
ChatGPT
Williams wins 42% (about 1 in 2 fights): a modest upset.
Claude
Soldić wins 45% (about 1 in 2 fights): a modest upset.
Timing 1 question
Chance it goes to a decision
Gemini
33%.
Other models' answers
ChatGPT
39%.
Claude
32%.
What if 1 question
If it goes to the judges, who wins?
Gemini
If it goes to the judges: Williams 30%, Soldić 70%.
Other models' answers
ChatGPT
If it goes to the judges: Williams 39%, Soldić 62%.
Claude
If it goes to the judges: Williams 63%, Soldić 38%.
Compared with others 2 questions
How does it compare with analyst picks?
Gemini
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Soldić (70%).
Other models' answers
ChatGPT
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Soldić (58%).
Claude
Of 41 analyst picks, 10 back Williams and 31 back Soldić. This model picks Williams (55%).
Which model is most confident on Williams, and which on Soldić?
Gemini
On Williams: Claude (55%). On Soldić: Gemini (70%).
How sure 4 questions
When was this forecast made, and by which model version?
Gemini
On 29 Sep 2026, by a model version the provider did not report.
Other models' answers
ChatGPT
On 27 Sep 2026, by gpt-6-astra.
Claude
On 27 Sep 2026, by claude-sonnet-5.
What can't the model know?
FightCard
Models research public information before the fight, such as records, styles, recent results and coverage. They cannot see inside training camps, injuries nobody has reported, or what happens on the night. A small chance is not no chance: outcomes the model rates at a few percent still happen, and big favourites lose sometimes.
How is "confidence" worked out?
FightCard
Confidence restates the favourite's win chance on a 10-step scale: the win chance in tens, rounded, so 55% is 6 of 10 and 95% or more is 10 of 10. 1 to 3 reads Low, 4 to 6 Medium and 7 to 10 High. A favourite usually has at least half the chance, so most picks show 5 or more. When the model has the fighters exactly even, there is no pick and no confidence level. It is not a separate judgement by the model.
What counts as a KO, a decision or a draw?
FightCard
KO/TKO includes referee, doctor and corner stoppages, and disqualifications. A decision includes a fight stopped early and scored on the judges' cards. A stoppage between rounds counts as a finish in the round that just ended. A draw and a no contest share one outcome.
After the fight 2 questions
Which model was closest?
Gemini
ChatGPT, which gave the actual result 24%.
Was the actual result in this model's top 3?
Gemini
Yes.
Other models' answers
Claude
No.
Version not reported · 29 Sep68 of 108 winner picks correct · 63% hit rate
AI-generated · Not betting advice · 21+. Gambling problem? Call 1-800-MY-RESET
Market Odds
No current consensus line is saved on this page.
Comments are currently closed while we finish moderation and privacy controls.