UFC Fight Night: Hooker vs. Parnasse
Salahdine Parnasse defeats Dan Hooker by KO/TKO
Round 1 · 2:35
Hooker vs Parnasse · UFC Fight Night: Hooker vs. Parnasse
Predictions summary
What happened
The result, the defining moments, and what the verdict means.
A Parnasse kick to the body doubled Hooker over and sent him retreating to the fence.
Parnasse followed him in with a punching flurry, a clean left hook inside it, and the referee stepped in. There was no knockdown-and-recovery phase — body kick to stoppage in one sequence.
The card's only scheduled five-rounder was over inside one, with no knockdown-and-recovery phase in between.
- Official UFC resultsUFC Paris: Hooker vs Parnasse — Results
- Round-by-round play-by-playUFC Paris 'Hooker vs. Parnasse' play-by-play, results & round scoring
Pre-fight analysis — how we saw it going in
Case for Hooker
Hooker is the only man in this fight with Octagon tape: 1,171 significant strikes landed from 2,405 thrown since his June 2014 debut, at 4.82 a minute, behind 77% takedown defence. He brings 38 professional fights to Parnasse’s 25, and a main event is territory he has occupied before against the division’s best.
Case for Parnasse
Parnasse is 23-2 and arrives on a five-fight winning streak in which every single result was a finish — four TKOs and a head-kick KO — including three defences of the KSW lightweight title and a first-round stoppage of Kenneth Cross in May. He is eight years younger, he has won in Paris twice, and Hooker has not finished anyone since November 2022.
What We Were Watching For
- Hooker’s last two fights both ended early and both went against him: an arm-triangle choke to Arman Tsarukyan in November 2025, then elbows and punches from Benoît Saint-Denis at UFC 325 in February.
- Every one of Parnasse’s last five wins ended inside two rounds. Hooker’s last finish was a body kick against Claudio Puelles in November 2022.
- Hooker absorbs 4.94 significant strikes a minute — marginally more than the 4.82 he lands — behind a 49% striking defence.
- The UFC records no striking statistics and 00:00 of Octagon time for Parnasse, so there is no promotional tape to plan against, and this is the card’s only five-round fight.
Records & career stats
- 24-14-0
- Record
- 23-2-0
- —
- Recent formRecent formWin–loss record over the fighter’s last five bouts, newest first, as carried in their UFC/FightMetric career stats.
- —
- New Zealand
- Nationality
- France
- 36
- Age
- 28
- —
- 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.
- —
- 77%
- Takedown defenseTD def.Takedown defenseThe percentage of opponents’ takedown attempts that are stuffed. Higher means harder to put on the mat. From UFC/FightMetric.
- —
- 09:50
- 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.
- 02:35
- Saigon Sports Club- Vietnam
- Team
- Atch Academy
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.
Before the fight (1)
Comments
Who Called It?
How the analysts' picks held up once the cage door closed.
Current pick evidence
Picked: Dan Hooker · KO/TKO · Round 3
Fight result: Salahdine Parnasse · KO/TKO
Believes the line undersells Hooker's chin, cardio and full camp, and expects him to weather an early Parnasse push and finish late.
“I think Dan Hooker is going to win by a third round TKO.”
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
Current pick evidence
Picked: Dan Hooker · KO/TKO
Fight result: Salahdine Parnasse · KO/TKO
MMA Mania's UFC Paris preview has Jesse Holland picking Dan Hooker by technical knockout.
Track record: winner called in 27 of 55 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 49.1% (27 hit, 28 miss, across 55 resolved calls). Method Accuracy 55.6% (15 hit, 12 miss, across 27 method-scored calls on 55 resolved calls). Round Accuracy: No round picks. Underdog Accuracy 27.8% (5 hit, 13 miss, across 18 underdog calls on 55 resolved calls).
- Winner Accuracy 49.1% 27 28
- Method Accuracy 55.6% 15 12
- Round AccuracyCalls the winner, not the round
- Underdog Accuracy 27.8% 5 13
Current pick evidence
Picked: Salahdine Parnasse · KO/TKO
Fight result: Salahdine Parnasse · KO/TKO
Picks Salahdine Parnasse to land a big shot and knock out Dan Hooker; no single round is committed.
“Pernal ends up landing a big shot and then ends up knocking Dan Hooker out.”
Track record: winner called in 11 of 14 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 78.6% (11 hit, 3 miss, across 14 resolved calls). Method Accuracy 30.0% (3 hit, 7 miss, across 10 method-scored calls on 14 resolved calls). Round Accuracy 33.3% (1 hit, 2 miss, across 3 round-scored calls on 14 resolved calls). Underdog Accuracy 100.0% (2 hit, 0 miss, across 2 underdog calls on 14 resolved calls).
- Winner Accuracy 78.6% 11 3
- Method Accuracy 30.0% 3 7
- Round Accuracy 33.3% 1 2
- Underdog Accuracy 100.0% 2
Current pick evidence
Picked: Salahdine Parnasse
Fight result: Salahdine Parnasse · KO/TKO
Picks Salahdine Parnasse inside the distance without selecting a specific finish method.
“I'm going to go with Parnasse here inside the distance.”
Track record: winner called in 8 of 11 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 72.7% (8 hit, 3 miss, across 11 resolved calls). Method Accuracy 50.0% (1 hit, 1 miss, across 2 method-scored calls on 11 resolved calls). Round Accuracy: No round picks. Underdog Accuracy: No underdog calls with a known pre-fight price.
- Winner Accuracy 72.7% 8 3
- Method Accuracy 50.0% 1 1
- Round AccuracyCalls the winner, not the round
- Underdog AccuracyNo underdog calls with a known pre-fight price
Current pick evidence
Picked: Salahdine Parnasse · KO/TKO
Fight result: Salahdine Parnasse · KO/TKO
FightIQ's public record lists Salahdine Parnasse as its pick over Dan Hooker.
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
Current pick evidence
Picked: Salahdine Parnasse · KO/TKO
Fight result: Salahdine Parnasse · KO/TKO
Believes Parnasse's rounded striking and grappling exploit Hooker's declining defence.
“So, we're going Parnas in the main event with just simply too many weapons, much athleticism, too much precision.”
Track record: winner called in 175 of 264 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 66.3% (175 hit, 89 miss, across 264 resolved calls). Method Accuracy 58.7% (61 hit, 43 miss, across 104 method-scored calls on 264 resolved calls). Round Accuracy 77.8% (7 hit, 2 miss, across 9 round-scored calls on 264 resolved calls). Underdog Accuracy 36.4% (12 hit, 21 miss, across 33 underdog calls on 264 resolved calls).
- Winner Accuracy 66.3% 175 89
- Method Accuracy 58.7% 61 43
- Round Accuracy 77.8% 7 2
- Underdog Accuracy 36.4% 12 21
Current pick evidence
Picked: Salahdine Parnasse · KO/TKO
Fight result: Salahdine Parnasse · KO/TKO
Picks Salahdine Parnasse's speed, straight left hand, and all-around game to stop Dan Hooker within the first three rounds.
“I think Salahdine Parnasse is able to TKO Dan Hooker inside the first three rounds.”
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
Current pick evidence
Picked: Salahdine Parnasse · KO/TKO · Round 3
Fight result: Salahdine Parnasse · KO/TKO
Sees Parnasse as the complete package in his athletic prime against an ageing, frequently finished Hooker.
“Give me Give me Saladin Parnasse to win this fight. I'll take him this to win this fight by third round knockout.”
Track record: winner called in 112 of 173 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 64.7% (112 hit, 61 miss, across 173 resolved calls). Method Accuracy 61.0% (61 hit, 39 miss, across 100 method-scored calls on 173 resolved calls). Round Accuracy 38.3% (18 hit, 29 miss, across 47 round-scored calls on 173 resolved calls). Underdog Accuracy 36.4% (8 hit, 14 miss, across 22 underdog calls on 173 resolved calls).
- Winner Accuracy 64.7% 112 61
- Method Accuracy 61.0% 61 39
- Round Accuracy 38.3% 18 29
- Underdog Accuracy 36.4% 8 14
Current pick evidence
Picked: Salahdine Parnasse · Dec
Fight result: Salahdine Parnasse · KO/TKO
Picks Salahdine Parnasse by decision in the UFC Paris main event.
“Give me Saladine Pis by decision.”
Track record: winner called in 20 of 31 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 64.5% (20 hit, 11 miss, across 31 resolved calls). Method Accuracy 33.3% (6 hit, 12 miss, across 18 method-scored calls on 31 resolved calls). Round Accuracy: No round picks. Underdog Accuracy 50.0% (2 hit, 2 miss, across 4 underdog calls on 31 resolved calls).
- Winner Accuracy 64.5% 20 11
- Method Accuracy 33.3% 6 12
- Round AccuracyCalls the winner, not the round
- Underdog Accuracy 50.0% 2 2
Current pick evidence
Picked: Salahdine Parnasse
Fight result: Salahdine Parnasse · KO/TKO
Picks Parnasse as the cleaner technical striker provided he manages the range rather than brawling.
“Now, I am picking Saldeen Parnasse because I think he's just more technical, he's cleaner, and the French typically have no issue with slowing a fight down and touching at range.”
Track record: winner called in 93 of 145 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 64.1% (93 hit, 52 miss, across 145 resolved calls). Method Accuracy 40.0% (2 hit, 3 miss, across 5 method-scored calls on 145 resolved calls). Round Accuracy: No qualifying picks. Underdog Accuracy 34.5% (10 hit, 19 miss, across 29 underdog calls on 145 resolved calls).
- Winner Accuracy 64.1% 93 52
- Method Accuracy 40.0% 2 3
- Round AccuracyNamed rounds — none on a correct call yet
- Underdog Accuracy 34.5% 10 19
Current pick evidence
Picked: Salahdine Parnasse · KO/TKO
Fight result: Salahdine Parnasse · KO/TKO
Picks Salahdine Parnasse by knockout; the transcript does not commit to a single round.
“Salahdine Parnasse via KO.”
Track record: winner called in 10 of 16 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 62.5% (10 hit, 6 miss, across 16 resolved calls). Method Accuracy 50.0% (3 hit, 3 miss, across 6 method-scored calls on 16 resolved calls). Round Accuracy: No round picks. Underdog Accuracy 50.0% (1 hit, 1 miss, across 2 underdog calls on 16 resolved calls).
- Winner Accuracy 62.5% 10 6
- Method Accuracy 50.0% 3 3
- Round AccuracyCalls the winner, not the round
- Underdog Accuracy 50.0% 1 1
Current pick evidence
Picked: Salahdine Parnasse · Dec
Fight result: Salahdine Parnasse · KO/TKO
Sees Parnasse as the clearly superior striker in his prime against a faded, one-dimensional Hooker.
“But I'm going to go Saladine Parnsi by decision.”
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
Current pick evidence
Picked: Salahdine Parnasse · KO/TKO · Round 2
Fight result: Salahdine Parnasse · KO/TKO
Picks Salahdine Parnasse to finish Dan Hooker with a body-shot TKO in round two.
“round two body shot TKO. Saladine Parnas gets the win.”
Track record: winner called in 11 of 18 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 61.1% (11 hit, 7 miss, across 18 resolved calls). Method Accuracy 75.0% (3 hit, 1 miss, across 4 method-scored calls on 18 resolved calls). Round Accuracy 0.0% (0 hit, 1 miss, across 1 round-scored calls on 18 resolved calls). Underdog Accuracy 50.0% (1 hit, 1 miss, across 2 underdog calls on 18 resolved calls).
- Winner Accuracy 61.1% 11 7
- Method Accuracy 75.0% 3 1
- Round Accuracy 0.0% 1
- Underdog Accuracy 50.0% 1 1
Current pick evidence
Picked: Salahdine Parnasse · KO/TKO · Round 3
Fight result: Salahdine Parnasse · KO/TKO
Picks Salahdine Parnasse to stop Dan Hooker in round three, citing Hooker's inactivity, accumulated punishment, and Parnasse's youth and speed.
“So yeah, Paress third round knockout.”
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
Current pick evidence
Picked: Salahdine Parnasse
Fight result: Salahdine Parnasse · KO/TKO
Picks Salahdine Parnasse and expects the UFC Paris main event to go the full distance.
“I'm going to pick Saladine Parnas. I think it's going to go the full distance.”
Track record: winner called in 28 of 53 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 52.8% (28 hit, 25 miss, across 53 resolved calls). Method Accuracy 47.1% (8 hit, 9 miss, across 17 method-scored calls on 53 resolved calls). Round Accuracy 71.4% (5 hit, 2 miss, across 7 round-scored calls on 53 resolved calls). Underdog Accuracy 20.0% (2 hit, 8 miss, across 10 underdog calls on 53 resolved calls).
- Winner Accuracy 52.8% 28 25
- Method Accuracy 47.1% 8 9
- Round Accuracy 71.4% 5 2
- Underdog Accuracy 20.0% 2 8
Current pick evidence
Picked: Salahdine Parnasse · KO/TKO
Fight result: Salahdine Parnasse · KO/TKO
Picks Salahdine Parnasse by knockout; the transcript mentions a range of rounds rather than one committed round.
“I'm going to go with Salahdine. Give me Salahdine by KO.”
Track record: winner called in 25 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 46.3% (25 hit, 29 miss, across 54 resolved calls). Method Accuracy 52.9% (9 hit, 8 miss, across 17 method-scored calls on 54 resolved calls). Round Accuracy 100.0% (1 hit, 0 miss, across 1 round-scored calls on 54 resolved calls). Underdog Accuracy 0.0% (0 hit, 7 miss, across 7 underdog calls on 54 resolved calls).
- Winner Accuracy 46.3% 25 29
- Method Accuracy 52.9% 9 8
- Round Accuracy 100.0% 1
- Underdog Accuracy 0.0% 7
Current pick evidence
Picked: Salahdine Parnasse · KO/TKO
Fight result: Salahdine Parnasse · KO/TKO
Picks Salahdine Parnasse by knockout.
“The prediction is going to be Parnasse by KO.”
Track record: winner called in 5 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 33.3% (5 hit, 10 miss, across 15 resolved calls). Method Accuracy 60.0% (3 hit, 2 miss, across 5 method-scored calls on 15 resolved calls). Round Accuracy: No round picks. Underdog Accuracy 0.0% (0 hit, 3 miss, across 3 underdog calls on 15 resolved calls).
- Winner Accuracy 33.3% 5 10
- Method Accuracy 60.0% 3 2
- Round AccuracyCalls the winner, not the round
- Underdog Accuracy 0.0% 3
Analyst picks: TheWagerZone ™ Hit; Dissection Of Violence Hit; Bedtime MMA Miss; FightIQ Hit; AJ Devito Hit; JakeGerberMMA Hit; DFS By The Numbers Hit; MMA Husky Hustler Hit; We Want Picks Hit; Fight IQ with Von Hit; HopperMMA Hit; Leftlane MMA Hit; James Lynch Hit; TonyHasDiedMMA Hit; Jesse Holland Miss; Uselyis Hit; FunkyBunch MMA Hit.
15 of 17 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 Parnasse · KO/TKO · R1
Closest probability ChatGPT put 78% on Parnasse.
AI 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 Parnasse
Most likely: Parnasse by KO/TKO, about 40 in 100
Win chance: Hooker 22%, Parnasse 78%.
Confidence 8 of 10 · High
Claude
61 of 101 winner picks correct · 60% hit rate
Pick Parnasse
Most likely: Parnasse by KO/TKO, about 34 in 100
Win chance: Hooker 28%, Parnasse 72%.
Confidence 7 of 10 · High
Gemini
68 of 108 winner picks correct · 63% hit rate
Pick Parnasse
Most likely: Parnasse by decision, about 37 in 100
Win chance: Hooker 37%, Parnasse 63%.
Confidence 6 of 10 · Medium
3 of 3 models pick Parnasse.
Questions
The result 7 questions
Who wins, and how likely?
ChatGPT
Parnasse: 78% (about 78 in 100 fights). Hooker: 22%.
Claude
Parnasse: 72% (about 72 in 100 fights). Hooker: 28%.
Gemini
Parnasse: 63% (about 63 in 100 fights). Hooker: 37%.
What is the single most likely outcome?
ChatGPT
Parnasse by KO/TKO: 40% (about 40 in 100).
Claude
Parnasse by KO/TKO: 34% (about 34 in 100).
Gemini
Parnasse by decision: 37% (about 37 in 100).
What are the three most likely outcomes, and why?
ChatGPT
1. Parnasse by KO/TKO (40%); 2. Parnasse by decision (25%); 3. Parnasse by submission (13%)
Claude
1. Parnasse by KO/TKO (34%); 2. Parnasse by submission (26%); 3. Hooker by KO/TKO (13%)
Gemini
1. Parnasse by decision (37%); 2. Parnasse by KO/TKO (18%); 3. Hooker by decision (17%)
How confident is the model?
ChatGPT
8 of 10, based on Parnasse's 78% win chance.
Claude
7 of 10, based on Parnasse's 72% win chance.
Gemini
6 of 10, based on Parnasse's 63% win chance.
Does it end early or go to the judges?
ChatGPT
Finish (KO/TKO or submission): 66%. Decision: 34%.
Claude
Finish (KO/TKO or submission): 78%. Decision: 22%.
Gemini
Finish (KO/TKO or submission): 46%. Decision: 54%.
How does Hooker win?
ChatGPT
Hooker wins 22%: KO/TKO 10%, submission 3%, decision 9%.
Claude
Hooker wins 28%: KO/TKO 13%, submission 5%, decision 10%.
Gemini
Hooker wins 37%: KO/TKO 16%, submission 4%, decision 17%.
How does Parnasse win?
ChatGPT
Parnasse wins 78%: KO/TKO 40%, submission 13%, decision 25%.
Claude
Parnasse wins 72%: KO/TKO 34%, submission 26%, decision 12%.
Gemini
Parnasse wins 63%: KO/TKO 18%, submission 8%, decision 37%.
What if 1 question
What is the upset path?
Gemini
Hooker's most likely upset: Hooker by decision (17%).
Compared with others 1 question
Do the models agree?
All models
The models agree: all 3 pick Parnasse.
After the fight 1 question
What happened vs what the model said?
ChatGPT
Result: Parnasse by KO/TKO in round 1. Parnasse by KO/TKO was the model's most likely outcome.
Claude
Result: Parnasse by KO/TKO in round 1. Parnasse by KO/TKO was the model's most likely outcome.
Gemini
Result: Parnasse by KO/TKO in round 1. Parnasse by KO/TKO was the model's number 2 outcome. Its most likely outcome was Parnasse by decision (37%).
More questions (19)
The result 7 questions
KO/TKO vs submission vs decision overall
ChatGPT
KO/TKO 50%, submission 16%, decision 34%.
Claude
KO/TKO 47%, submission 31%, decision 22%.
Gemini
KO/TKO 34%, submission 12%, decision 54%.
Who is more likely to finish the other?
ChatGPT
Parnasse: 53%, against 13% for Hooker.
Claude
Parnasse: 60%, against 18% for Hooker.
Gemini
Parnasse: 26%, against 20% for Hooker.
Can Hooker get the finish? Can Parnasse?
ChatGPT
Hooker: 13% (KO/TKO 10%, submission 3%). Parnasse: 53% (KO/TKO 40%, submission 13%).
Claude
Hooker: 18% (KO/TKO 13%, submission 5%). Parnasse: 60% (KO/TKO 34%, submission 26%).
Gemini
Hooker: 20% (KO/TKO 16%, submission 4%). Parnasse: 26% (KO/TKO 18%, submission 8%).
Who is more likely to be knocked out, and who to be submitted?
ChatGPT
Hooker is knocked out in 40% and submitted in 13%. Parnasse is knocked out in 10% and submitted in 3%.
Claude
Hooker is knocked out in 34% and submitted in 26%. Parnasse is knocked out in 13% and submitted in 5%.
Gemini
Hooker is knocked out in 18% and submitted in 8%. Parnasse is knocked out in 16% and submitted in 4%.
How lopsided is this fight?
ChatGPT
Lopsided: 78% vs 22%.
Claude
Lopsided: 72% vs 28%.
Gemini
Lopsided: 63% vs 37%.
Each fighter's single most likely way to win
Gemini
Hooker by decision: 17%. Parnasse by decision: 37%.
How big an upset would it be if the underdog wins?
ChatGPT
Hooker wins 22% (about 1 in 5 fights): a big upset.
Claude
Hooker wins 28% (about 1 in 4 fights): a big upset.
Gemini
Hooker wins 37% (about 1 in 3 fights): a big upset.
Timing 1 question
Chance it goes to a decision
ChatGPT
34%.
Claude
22%.
Gemini
54%.
What if 1 question
If it goes to the judges, who wins?
ChatGPT
If it goes to the judges: Hooker 27%, Parnasse 74%.
Claude
If it goes to the judges: Hooker 46%, Parnasse 55%.
Gemini
If it goes to the judges: Hooker 32%, Parnasse 69%.
Compared with others 5 questions
Where does this model differ from the others?
Claude
Biggest difference: Parnasse by decision, 12% here against 31% on average for the others.
How does it compare with analyst picks?
ChatGPT
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (78%).
Claude
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (72%).
Gemini
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (63%).
Which model is most confident on Hooker, and which on Parnasse?
All models
On Hooker: Gemini (37%). On Parnasse: ChatGPT (78%).
Where do the models disagree most?
All models
Parnasse by decision: from 12% (Claude) to 37% (Gemini).
Which analyst agrees most with this model?
Gemini
MMA Husky Hustler (Parnasse by decision) and HopperMMA (Parnasse by decision): the same winner and method as this model, tied; this model favours Parnasse, most likely by decision.
How sure 4 questions
When was this forecast made, and by which model version?
ChatGPT
On 5 Sep 2026, by gpt-5.6-sol.
Claude
On 5 Sep 2026, by claude-sonnet-5.
Gemini
On 5 Sep 2026, by gemini-web-flash.
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 1 question
Was the actual result in this model's top 3?
All models
Yes.
ChatGPT
Pick
Parnasse
Confidence 8 of 10 · High
Most likely: Parnasse by KO/TKO, about 40 in 100
The model's predicted finish round: 3.
Win chance: Hooker 22%, Parnasse 78%.
Most likely outcomes
- Parnasse by KO/TKO40%
- Parnasse by decision25%
- Parnasse by submission13%
- KO/TKO: Hooker 10%, Parnasse 40%.
- Submission: Hooker 3%, Parnasse 13%.
- Decision: Hooker 9%, Parnasse 25%.
Questions
The result 7 questions
Who wins, and how likely?
ChatGPT
Parnasse: 78% (about 78 in 100 fights). Hooker: 22%.
Other models' answers
Claude
Parnasse: 72% (about 72 in 100 fights). Hooker: 28%.
Gemini
Parnasse: 63% (about 63 in 100 fights). Hooker: 37%.
What is the single most likely outcome?
ChatGPT
Parnasse by KO/TKO: 40% (about 40 in 100).
Other models' answers
Claude
Parnasse by KO/TKO: 34% (about 34 in 100).
Gemini
Parnasse by decision: 37% (about 37 in 100).
What are the three most likely outcomes, and why?
ChatGPT
1. Parnasse by KO/TKO (40%); 2. Parnasse by decision (25%); 3. Parnasse by submission (13%)
Other models' answers
Claude
1. Parnasse by KO/TKO (34%); 2. Parnasse by submission (26%); 3. Hooker by KO/TKO (13%)
Gemini
1. Parnasse by decision (37%); 2. Parnasse by KO/TKO (18%); 3. Hooker by decision (17%)
How confident is the model?
ChatGPT
8 of 10, based on Parnasse's 78% win chance.
Other models' answers
Claude
7 of 10, based on Parnasse's 72% win chance.
Gemini
6 of 10, based on Parnasse's 63% win chance.
Does it end early or go to the judges?
ChatGPT
Finish (KO/TKO or submission): 66%. Decision: 34%.
Other models' answers
Claude
Finish (KO/TKO or submission): 78%. Decision: 22%.
Gemini
Finish (KO/TKO or submission): 46%. Decision: 54%.
How does Hooker win?
ChatGPT
Hooker wins 22%: KO/TKO 10%, submission 3%, decision 9%.
Other models' answers
Claude
Hooker wins 28%: KO/TKO 13%, submission 5%, decision 10%.
Gemini
Hooker wins 37%: KO/TKO 16%, submission 4%, decision 17%.
How does Parnasse win?
ChatGPT
Parnasse wins 78%: KO/TKO 40%, submission 13%, decision 25%.
Other models' answers
Claude
Parnasse wins 72%: KO/TKO 34%, submission 26%, decision 12%.
Gemini
Parnasse wins 63%: KO/TKO 18%, submission 8%, decision 37%.
Compared with others 1 question
Do the models agree?
ChatGPT
The models agree: all 3 pick Parnasse.
After the fight 1 question
What happened vs what the model said?
ChatGPT
Result: Parnasse by KO/TKO in round 1. Parnasse by KO/TKO was the model's most likely outcome.
Other models' answers
Gemini
Result: Parnasse by KO/TKO in round 1. Parnasse by KO/TKO was the model's number 2 outcome. Its most likely outcome was Parnasse by decision (37%).
More questions (16)
The result 6 questions
KO/TKO vs submission vs decision overall
ChatGPT
KO/TKO 50%, submission 16%, decision 34%.
Other models' answers
Claude
KO/TKO 47%, submission 31%, decision 22%.
Gemini
KO/TKO 34%, submission 12%, decision 54%.
Who is more likely to finish the other?
ChatGPT
Parnasse: 53%, against 13% for Hooker.
Other models' answers
Claude
Parnasse: 60%, against 18% for Hooker.
Gemini
Parnasse: 26%, against 20% for Hooker.
Can Hooker get the finish? Can Parnasse?
ChatGPT
Hooker: 13% (KO/TKO 10%, submission 3%). Parnasse: 53% (KO/TKO 40%, submission 13%).
Other models' answers
Claude
Hooker: 18% (KO/TKO 13%, submission 5%). Parnasse: 60% (KO/TKO 34%, submission 26%).
Gemini
Hooker: 20% (KO/TKO 16%, submission 4%). Parnasse: 26% (KO/TKO 18%, submission 8%).
Who is more likely to be knocked out, and who to be submitted?
ChatGPT
Hooker is knocked out in 40% and submitted in 13%. Parnasse is knocked out in 10% and submitted in 3%.
Other models' answers
Claude
Hooker is knocked out in 34% and submitted in 26%. Parnasse is knocked out in 13% and submitted in 5%.
Gemini
Hooker is knocked out in 18% and submitted in 8%. Parnasse is knocked out in 16% and submitted in 4%.
How lopsided is this fight?
ChatGPT
Lopsided: 78% vs 22%.
Other models' answers
Claude
Lopsided: 72% vs 28%.
Gemini
Lopsided: 63% vs 37%.
How big an upset would it be if the underdog wins?
ChatGPT
Hooker wins 22% (about 1 in 5 fights): a big upset.
Other models' answers
Claude
Hooker wins 28% (about 1 in 4 fights): a big upset.
Gemini
Hooker wins 37% (about 1 in 3 fights): a big upset.
Timing 1 question
Chance it goes to a decision
ChatGPT
34%.
Other models' answers
Claude
22%.
Gemini
54%.
What if 1 question
If it goes to the judges, who wins?
ChatGPT
If it goes to the judges: Hooker 27%, Parnasse 74%.
Other models' answers
Claude
If it goes to the judges: Hooker 46%, Parnasse 55%.
Gemini
If it goes to the judges: Hooker 32%, Parnasse 69%.
Compared with others 3 questions
How does it compare with analyst picks?
ChatGPT
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (78%).
Other models' answers
Claude
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (72%).
Gemini
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (63%).
Which model is most confident on Hooker, and which on Parnasse?
ChatGPT
On Hooker: Gemini (37%). On Parnasse: ChatGPT (78%).
Where do the models disagree most?
ChatGPT
Parnasse by decision: from 12% (Claude) to 37% (Gemini).
How sure 4 questions
When was this forecast made, and by which model version?
ChatGPT
On 5 Sep 2026, by gpt-5.6-sol.
Other models' answers
Claude
On 5 Sep 2026, by claude-sonnet-5.
Gemini
On 5 Sep 2026, by gemini-web-flash.
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 1 question
Was the actual result in this model's top 3?
ChatGPT
Yes.
gpt-5.6-sol · 5 Sep63 of 108 winner picks correct · 58% hit rate
Claude
Pick
Parnasse
Confidence 7 of 10 · High
Most likely: Parnasse by KO/TKO, about 34 in 100
The model's predicted finish round: 3.
Win chance: Hooker 28%, Parnasse 72%.
Most likely outcomes
- Parnasse by KO/TKO34%
- Parnasse by submission26%
- Hooker by KO/TKO13%
- KO/TKO: Hooker 13%, Parnasse 34%.
- Submission: Hooker 5%, Parnasse 26%.
- Decision: Hooker 10%, Parnasse 12%.
Questions
The result 7 questions
Who wins, and how likely?
Claude
Parnasse: 72% (about 72 in 100 fights). Hooker: 28%.
Other models' answers
ChatGPT
Parnasse: 78% (about 78 in 100 fights). Hooker: 22%.
Gemini
Parnasse: 63% (about 63 in 100 fights). Hooker: 37%.
What is the single most likely outcome?
Claude
Parnasse by KO/TKO: 34% (about 34 in 100).
Other models' answers
ChatGPT
Parnasse by KO/TKO: 40% (about 40 in 100).
Gemini
Parnasse by decision: 37% (about 37 in 100).
What are the three most likely outcomes, and why?
Claude
1. Parnasse by KO/TKO (34%); 2. Parnasse by submission (26%); 3. Hooker by KO/TKO (13%)
Other models' answers
ChatGPT
1. Parnasse by KO/TKO (40%); 2. Parnasse by decision (25%); 3. Parnasse by submission (13%)
Gemini
1. Parnasse by decision (37%); 2. Parnasse by KO/TKO (18%); 3. Hooker by decision (17%)
How confident is the model?
Claude
7 of 10, based on Parnasse's 72% win chance.
Other models' answers
ChatGPT
8 of 10, based on Parnasse's 78% win chance.
Gemini
6 of 10, based on Parnasse's 63% win chance.
Does it end early or go to the judges?
Claude
Finish (KO/TKO or submission): 78%. Decision: 22%.
Other models' answers
ChatGPT
Finish (KO/TKO or submission): 66%. Decision: 34%.
Gemini
Finish (KO/TKO or submission): 46%. Decision: 54%.
How does Hooker win?
Claude
Hooker wins 28%: KO/TKO 13%, submission 5%, decision 10%.
Other models' answers
ChatGPT
Hooker wins 22%: KO/TKO 10%, submission 3%, decision 9%.
Gemini
Hooker wins 37%: KO/TKO 16%, submission 4%, decision 17%.
How does Parnasse win?
Claude
Parnasse wins 72%: KO/TKO 34%, submission 26%, decision 12%.
Other models' answers
ChatGPT
Parnasse wins 78%: KO/TKO 40%, submission 13%, decision 25%.
Gemini
Parnasse wins 63%: KO/TKO 18%, submission 8%, decision 37%.
Compared with others 1 question
Do the models agree?
Claude
The models agree: all 3 pick Parnasse.
After the fight 1 question
What happened vs what the model said?
Claude
Result: Parnasse by KO/TKO in round 1. Parnasse by KO/TKO was the model's most likely outcome.
Other models' answers
Gemini
Result: Parnasse by KO/TKO in round 1. Parnasse by KO/TKO was the model's number 2 outcome. Its most likely outcome was Parnasse by decision (37%).
More questions (17)
The result 6 questions
KO/TKO vs submission vs decision overall
Claude
KO/TKO 47%, submission 31%, decision 22%.
Other models' answers
ChatGPT
KO/TKO 50%, submission 16%, decision 34%.
Gemini
KO/TKO 34%, submission 12%, decision 54%.
Who is more likely to finish the other?
Claude
Parnasse: 60%, against 18% for Hooker.
Other models' answers
ChatGPT
Parnasse: 53%, against 13% for Hooker.
Gemini
Parnasse: 26%, against 20% for Hooker.
Can Hooker get the finish? Can Parnasse?
Claude
Hooker: 18% (KO/TKO 13%, submission 5%). Parnasse: 60% (KO/TKO 34%, submission 26%).
Other models' answers
ChatGPT
Hooker: 13% (KO/TKO 10%, submission 3%). Parnasse: 53% (KO/TKO 40%, submission 13%).
Gemini
Hooker: 20% (KO/TKO 16%, submission 4%). Parnasse: 26% (KO/TKO 18%, submission 8%).
Who is more likely to be knocked out, and who to be submitted?
Claude
Hooker is knocked out in 34% and submitted in 26%. Parnasse is knocked out in 13% and submitted in 5%.
Other models' answers
ChatGPT
Hooker is knocked out in 40% and submitted in 13%. Parnasse is knocked out in 10% and submitted in 3%.
Gemini
Hooker is knocked out in 18% and submitted in 8%. Parnasse is knocked out in 16% and submitted in 4%.
How lopsided is this fight?
Claude
Lopsided: 72% vs 28%.
Other models' answers
ChatGPT
Lopsided: 78% vs 22%.
Gemini
Lopsided: 63% vs 37%.
How big an upset would it be if the underdog wins?
Claude
Hooker wins 28% (about 1 in 4 fights): a big upset.
Other models' answers
ChatGPT
Hooker wins 22% (about 1 in 5 fights): a big upset.
Gemini
Hooker wins 37% (about 1 in 3 fights): a big upset.
Timing 1 question
Chance it goes to a decision
Claude
22%.
Other models' answers
ChatGPT
34%.
Gemini
54%.
What if 1 question
If it goes to the judges, who wins?
Claude
If it goes to the judges: Hooker 46%, Parnasse 55%.
Other models' answers
ChatGPT
If it goes to the judges: Hooker 27%, Parnasse 74%.
Gemini
If it goes to the judges: Hooker 32%, Parnasse 69%.
Compared with others 4 questions
Where does this model differ from the others?
Claude
Biggest difference: Parnasse by decision, 12% here against 31% on average for the others.
How does it compare with analyst picks?
Claude
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (72%).
Other models' answers
ChatGPT
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (78%).
Gemini
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (63%).
Which model is most confident on Hooker, and which on Parnasse?
Claude
On Hooker: Gemini (37%). On Parnasse: ChatGPT (78%).
Where do the models disagree most?
Claude
Parnasse by decision: from 12% (Claude) to 37% (Gemini).
How sure 4 questions
When was this forecast made, and by which model version?
Claude
On 5 Sep 2026, by claude-sonnet-5.
Other models' answers
ChatGPT
On 5 Sep 2026, by gpt-5.6-sol.
Gemini
On 5 Sep 2026, by gemini-web-flash.
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 1 question
Was the actual result in this model's top 3?
Claude
Yes.
claude-sonnet-5 · 5 Sep61 of 101 winner picks correct · 60% hit rate
Gemini
Pick
Parnasse
Confidence 6 of 10 · Medium
Most likely: Parnasse by decision, about 37 in 100
Win chance: Hooker 37%, Parnasse 63%.
Most likely outcomes
- Parnasse by decision37%
- Parnasse by KO/TKO18%
- Hooker by decision17%
- KO/TKO: Hooker 16%, Parnasse 18%.
- Submission: Hooker 4%, Parnasse 8%.
- Decision: Hooker 17%, Parnasse 37%.
Questions
The result 7 questions
Who wins, and how likely?
Gemini
Parnasse: 63% (about 63 in 100 fights). Hooker: 37%.
Other models' answers
ChatGPT
Parnasse: 78% (about 78 in 100 fights). Hooker: 22%.
Claude
Parnasse: 72% (about 72 in 100 fights). Hooker: 28%.
What is the single most likely outcome?
Gemini
Parnasse by decision: 37% (about 37 in 100).
Other models' answers
ChatGPT
Parnasse by KO/TKO: 40% (about 40 in 100).
Claude
Parnasse by KO/TKO: 34% (about 34 in 100).
What are the three most likely outcomes, and why?
Gemini
1. Parnasse by decision (37%); 2. Parnasse by KO/TKO (18%); 3. Hooker by decision (17%)
Other models' answers
ChatGPT
1. Parnasse by KO/TKO (40%); 2. Parnasse by decision (25%); 3. Parnasse by submission (13%)
Claude
1. Parnasse by KO/TKO (34%); 2. Parnasse by submission (26%); 3. Hooker by KO/TKO (13%)
How confident is the model?
Gemini
6 of 10, based on Parnasse's 63% win chance.
Other models' answers
ChatGPT
8 of 10, based on Parnasse's 78% win chance.
Claude
7 of 10, based on Parnasse's 72% win chance.
Does it end early or go to the judges?
Gemini
Finish (KO/TKO or submission): 46%. Decision: 54%.
Other models' answers
ChatGPT
Finish (KO/TKO or submission): 66%. Decision: 34%.
Claude
Finish (KO/TKO or submission): 78%. Decision: 22%.
How does Hooker win?
Gemini
Hooker wins 37%: KO/TKO 16%, submission 4%, decision 17%.
Other models' answers
ChatGPT
Hooker wins 22%: KO/TKO 10%, submission 3%, decision 9%.
Claude
Hooker wins 28%: KO/TKO 13%, submission 5%, decision 10%.
How does Parnasse win?
Gemini
Parnasse wins 63%: KO/TKO 18%, submission 8%, decision 37%.
Other models' answers
ChatGPT
Parnasse wins 78%: KO/TKO 40%, submission 13%, decision 25%.
Claude
Parnasse wins 72%: KO/TKO 34%, submission 26%, decision 12%.
What if 1 question
What is the upset path?
Gemini
Hooker's most likely upset: Hooker by decision (17%).
Compared with others 1 question
Do the models agree?
Gemini
The models agree: all 3 pick Parnasse.
After the fight 1 question
What happened vs what the model said?
Gemini
Result: Parnasse by KO/TKO in round 1. Parnasse by KO/TKO was the model's number 2 outcome. Its most likely outcome was Parnasse by decision (37%).
Other models' answers
ChatGPT
Result: Parnasse by KO/TKO in round 1. Parnasse by KO/TKO was the model's most likely outcome.
Claude
Result: Parnasse by KO/TKO in round 1. Parnasse by KO/TKO was the model's most likely outcome.
More questions (18)
The result 7 questions
KO/TKO vs submission vs decision overall
Gemini
KO/TKO 34%, submission 12%, decision 54%.
Other models' answers
ChatGPT
KO/TKO 50%, submission 16%, decision 34%.
Claude
KO/TKO 47%, submission 31%, decision 22%.
Who is more likely to finish the other?
Gemini
Parnasse: 26%, against 20% for Hooker.
Other models' answers
ChatGPT
Parnasse: 53%, against 13% for Hooker.
Claude
Parnasse: 60%, against 18% for Hooker.
Can Hooker get the finish? Can Parnasse?
Gemini
Hooker: 20% (KO/TKO 16%, submission 4%). Parnasse: 26% (KO/TKO 18%, submission 8%).
Other models' answers
ChatGPT
Hooker: 13% (KO/TKO 10%, submission 3%). Parnasse: 53% (KO/TKO 40%, submission 13%).
Claude
Hooker: 18% (KO/TKO 13%, submission 5%). Parnasse: 60% (KO/TKO 34%, submission 26%).
Who is more likely to be knocked out, and who to be submitted?
Gemini
Hooker is knocked out in 18% and submitted in 8%. Parnasse is knocked out in 16% and submitted in 4%.
Other models' answers
ChatGPT
Hooker is knocked out in 40% and submitted in 13%. Parnasse is knocked out in 10% and submitted in 3%.
Claude
Hooker is knocked out in 34% and submitted in 26%. Parnasse is knocked out in 13% and submitted in 5%.
How lopsided is this fight?
Gemini
Lopsided: 63% vs 37%.
Other models' answers
ChatGPT
Lopsided: 78% vs 22%.
Claude
Lopsided: 72% vs 28%.
Each fighter's single most likely way to win
Gemini
Hooker by decision: 17%. Parnasse by decision: 37%.
How big an upset would it be if the underdog wins?
Gemini
Hooker wins 37% (about 1 in 3 fights): a big upset.
Other models' answers
ChatGPT
Hooker wins 22% (about 1 in 5 fights): a big upset.
Claude
Hooker wins 28% (about 1 in 4 fights): a big upset.
Timing 1 question
Chance it goes to a decision
Gemini
54%.
Other models' answers
ChatGPT
34%.
Claude
22%.
What if 1 question
If it goes to the judges, who wins?
Gemini
If it goes to the judges: Hooker 32%, Parnasse 69%.
Other models' answers
ChatGPT
If it goes to the judges: Hooker 27%, Parnasse 74%.
Claude
If it goes to the judges: Hooker 46%, Parnasse 55%.
Compared with others 4 questions
How does it compare with analyst picks?
Gemini
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (63%).
Other models' answers
ChatGPT
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (78%).
Claude
Of 17 analyst picks, 2 back Hooker and 15 back Parnasse. This model picks Parnasse (72%).
Which model is most confident on Hooker, and which on Parnasse?
Gemini
On Hooker: Gemini (37%). On Parnasse: ChatGPT (78%).
Where do the models disagree most?
Gemini
Parnasse by decision: from 12% (Claude) to 37% (Gemini).
Which analyst agrees most with this model?
Gemini
MMA Husky Hustler (Parnasse by decision) and HopperMMA (Parnasse by decision): the same winner and method as this model, tied; this model favours Parnasse, most likely by decision.
How sure 4 questions
When was this forecast made, and by which model version?
Gemini
On 5 Sep 2026, by gemini-web-flash.
Other models' answers
ChatGPT
On 5 Sep 2026, by gpt-5.6-sol.
Claude
On 5 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 1 question
Was the actual result in this model's top 3?
Gemini
Yes.
gemini-web-flash · 5 Sep68 of 108 winner picks correct · 63% hit rate
AI-generated · Not betting advice · 21+. Gambling problem? Call 1-800-MY-RESET
Market Odds
How the market called it — the final pre-fight line against the result, not betting advice.
Market read · 5 sportsbooks
Favoured: Parnasse (81%) Called it
Parnasse defeats Hooker · KO/TKO R1

















Comments are currently closed while we finish moderation and privacy controls.