Noche UFC: Silva vs. Delgado  12 Sep 2026 · Desert Diamond Arena, Glendale, Arizona, US

Rongzhu defeats Rafa Garcia by unanimous decision

Loss Rafa Garcia 19-5-0
Win Rongzhu 29-6-0
Unanimous decision

Round 3 · 5:00

Garcia vs Rongzhu — Lightweight · Noche UFC: Silva vs. Delgado

Predictions summary

Fight details

The verified result and matchup record are available above. Analysis and a fight narrative have not been published for this bout.

Records & career stats
Garcia vs Rongzhu
19-4-0
Record
28-6-0
—
Recent formRecent formWin–loss record over the fighter’s last five bouts, newest first, as carried in their UFC/FightMetric career stats.
—
Mexico
Nationality
China
32
Age
26
5′7″170 cm
Height — Rongzhu leads
5′9″175 cm
70″178 cm
Reach — Rongzhu leads
71″180 cm
—
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.
—
—
Finish rateFinish %Finish rateThe share of a fighter’s wins that ended inside the distance — by KO/TKO or submission — rather than going to the judges’ scorecards. Higher means more finishes.
—
2
Wins by KO/TKOKO wins — Rongzhu leads
16
8
Wins by submissionSub wins — Garcia leads
6
4.33
Sig. strikes landed / minStr / min — Rongzhu leadsSignificant strikes landed per minuteAverage number of significant strikes a fighter lands for every minute of fight time — a read on striking output and pace. From UFC/FightMetric career stats.
6.05
4.68
Sig. strikes absorbed / minAbs / min — Garcia leadsSignificant strikes absorbed per minuteAverage number of significant strikes a fighter takes for every minute of fight time. Lower is better — it means they get hit less often. From UFC/FightMetric career stats.
5.38
61%
Striking defenseStrike def. — Garcia leadsStriking defenseThe percentage of opponents’ significant strikes that do not land — strikes slipped, blocked or evaded. Higher is better. Not the same as striking accuracy, which counts your own strikes that land. From UFC/FightMetric.
54%
77%
Takedown defenseTD def. — Rongzhu leadsTakedown defenseThe percentage of opponents’ takedown attempts that are stuffed. Higher means harder to put on the mat. From UFC/FightMetric.
85%
13:40
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.
11:33

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.

Comments

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

Who Called It?

How the analysts' picks held up once the cage door closed.

The MMA Guru
Hear it — 8:12 The MMA Guru on YouTube ↗

Current pick evidence

Picked: Rafa Garcia

Fight result: Rongzhu · Decision

Picks Rafa Garcia to win.

“I'm going to go with Rafa Garcia.”

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).

View full track record (322 calls)
MMA JOEY
Hear it — 7:26 MMA JOEY on YouTube ↗

Current pick evidence

Picked: Rafa Garcia · Dec

Fight result: Rongzhu · Decision

Picks Rafa Garcia by decision.

“I'll go Rafa Garcia. I'll say 29-28 decision win.”

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).

View full track record (125 calls)
HopperMMA
Hear it — 4:22 HopperMMA on YouTube ↗

Current pick evidence

Picked: Rafa Garcia · Dec

Fight result: Rongzhu · Decision

Picks Rafa Garcia by decision.

“I'm going to go with Rafa Garcia 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).

View full track record (148 calls)
Live Dogs MMA
Hear it — 1:18 Live Dogs MMA on YouTube ↗

Current pick evidence

Picked: Rongzhu · KO/TKO

Fight result: Rongzhu · Decision

Picks Rongzhu by KO.

“Give me Rongzhu by KO.”

Track record: winner called in 10 of 13 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 76.9% (10 hit, 3 miss, across 13 resolved calls). Method Accuracy 0.0% (0 hit, 3 miss, across 3 method-scored calls on 13 resolved calls). Round Accuracy: No round picks. Underdog Accuracy 100.0% (1 hit, 0 miss, across 1 underdog calls on 13 resolved calls).

View full track record (13 calls)
Bedtime MMA
Hear it — 6:09 Bedtime MMA on YouTube ↗

Current pick evidence

Picked: Rongzhu · Dec

Fight result: Rongzhu · Decision

Picks Rongzhu by Decision.

“I'm going to say Rongzhu wins this one by decision, but it's close.”

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).

View full track record (185 calls)
TheWeasle
Hear it — 11:27 TheWeasle on YouTube ↗

Current pick evidence

Picked: Rongzhu · Dec

Fight result: Rongzhu · Decision

Picks Rongzhu by Decision.

“I think Rongzhu wins the fight by decision.”

Track record: winner called in 115 of 163 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 70.6% (115 hit, 48 miss, across 163 resolved calls). Method Accuracy 61.8% (47 hit, 29 miss, across 76 method-scored calls on 163 resolved calls). Round Accuracy 36.5% (19 hit, 33 miss, across 52 round-scored calls on 163 resolved calls). Underdog Accuracy 52.9% (9 hit, 8 miss, across 17 underdog calls on 163 resolved calls).

View full track record (163 calls)
Jimbo Ortega MMA
Hear it — 4:01 Jimbo Ortega MMA on YouTube ↗

Current pick evidence

Picked: Rongzhu · Dec

Fight result: Rongzhu · Decision

Picks Rong Zhu by decision; the caption garbles the name, but the preceding matchup context identifies Rafa Garcia vs Rong Zhu.

“So, get me wrong, Zu. I am going to go with decision.”

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).

View full track record (56 calls)
MMA Lock of the Night
Hear it — 1:31 MMA Lock of the Night on YouTube ↗

Current pick evidence

Picked: Rongzhu · Dec

Fight result: Rongzhu · Decision

Picks Rongzhu by decision; the captions render the name as Rong Zhu.

“leading to Rong Zhu winning this fight on the scorecards.”

Track record: winner called in 85 of 126 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 67.5% (85 hit, 41 miss, across 126 resolved calls). Method Accuracy 59.5% (25 hit, 17 miss, across 42 method-scored calls on 126 resolved calls). Round Accuracy 55.6% (5 hit, 4 miss, across 9 round-scored calls on 126 resolved calls). Underdog Accuracy 36.8% (7 hit, 12 miss, across 19 underdog calls on 126 resolved calls).

View full track record (126 calls)
DFS By The Numbers
Hear it — 6:37 DFS By The Numbers on YouTube ↗

Current pick evidence

Picked: Rongzhu · Dec

Fight result: Rongzhu · Decision

Picks Rongzhu by decision.

“I'm going to go with Rongzhu to win this fight by decision.”

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).

View full track record (173 calls)
MMA Prediction Guru (MMAPG)
Source unavailable — 17:53 MMA Prediction Guru (MMAPG) on YouTube ↗

Current pick evidence

Picked: Rongzhu

Fight result: Rongzhu · Decision

Picks Rongzhu to win.

“Give me Rongzhu here.”

Track record: winner called in 41 of 69 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 59.4% (41 hit, 28 miss, across 69 resolved calls). Method Accuracy 57.7% (15 hit, 11 miss, across 26 method-scored calls on 69 resolved calls). Round Accuracy 12.5% (1 hit, 7 miss, across 8 round-scored calls on 69 resolved calls). Underdog Accuracy 30.8% (4 hit, 9 miss, across 13 underdog calls on 69 resolved calls).

View full track record (69 calls)
Kunath
Hear it — 22:29 Kunath on YouTube ↗

Current pick evidence

Picked: Rongzhu · Dec

Fight result: Rongzhu · Decision

Picks Rongzhu by decision.

“Give me Rongzhu by decision.”

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).

View full track record (65 calls)
Half The Battle
Hear it — 35:58 Half The Battle on YouTube ↗

Current pick evidence

Picked: Rongzhu

Fight result: Rongzhu · Decision

Picks Rongzhu to win.

“I got Rongzhu to come out here and defeat Rafa Garcia.”

Track record: winner called in 58 of 109 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 53.2% (58 hit, 51 miss, across 109 resolved calls). Method Accuracy 71.4% (10 hit, 4 miss, across 14 method-scored calls on 109 resolved calls). Round Accuracy 66.7% (2 hit, 1 miss, across 3 round-scored calls on 109 resolved calls). Underdog Accuracy 21.4% (6 hit, 22 miss, across 28 underdog calls on 109 resolved calls).

View full track record (109 calls)

Analyst picks: Live Dogs MMA Hit; Bedtime MMA Hit; TheWeasle Hit; Jimbo Ortega MMA Hit; MMA Lock of the Night Hit; The MMA Guru Miss; DFS By The Numbers Hit; MMA JOEY Miss; HopperMMA Miss; MMA Prediction Guru (MMAPG) Hit; Kunath Hit; Half The Battle Hit.

9 of 12 nailed it.

Chart: selected analyst picks, not a win probability. Pill badge: Winner hit rate (total scored picks before this event).

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 Rongzhu · Decision · R3

Closest probability ChatGPT put 59% on Rongzhu.

ChatGPTForecast: 63 of 108 winner picks correct · 58% hit rate
41% Garcia
59% Rongzhu
PickRongzhu · DecisionActualRongzhu · Decision · R3
WinnerHitMethodHitRoundNot applicable — decisions have no finishing roundHistoric market favouriteHistoric market favourite: FavouriteThe selected fighter had the higher market-implied chance of winning.Historic market favourite: favourite call
ClaudeForecast: 61 of 101 winner picks correct · 60% hit rate
42% Garcia
58% Rongzhu
PickRongzhu · KO/TKO · R2ActualRongzhu · Decision · R3
WinnerHitMethodMissRoundNot applicable — decisions have no finishing roundHistoric market favouriteHistoric market favourite: FavouriteThe selected fighter had the higher market-implied chance of winning.Historic market favourite: favourite call
GeminiForecast: 68 of 108 winner picks correct · 63% hit rate
44% Garcia
56% Rongzhu
PickRongzhu · DecisionActualRongzhu · Decision · R3
WinnerHitMethodHitRoundNot applicable — decisions have no finishing roundHistoric market favouriteHistoric market favourite: FavouriteThe selected fighter had the higher market-implied chance of winning.Historic market favourite: favourite call
AI Predictions — latest pre-fight callsFrozen 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 Rongzhu

    Most likely: Rongzhu by decision, about 32 in 100

    Win chance: Garcia 41%, Rongzhu 59%.

    gpt-5.6-sol · 5 Sep

    Confidence 6 of 10 · Medium

  • Claude

    61 of 101 winner picks correct · 60% hit rate

    Pick Rongzhu

    Most likely: Rongzhu by KO/TKO, about 30 in 100

    Win chance: Garcia 42%, Rongzhu 58%.

    claude-sonnet-5 · 5 Sep

    Confidence 6 of 10 · Medium

  • Gemini

    68 of 108 winner picks correct · 63% hit rate

    Pick Rongzhu

    Most likely: Rongzhu by decision, about 36 in 100

    Win chance: Garcia 44%, Rongzhu 56%.

    Version not reported · 5 Sep

    Confidence 6 of 10 · Medium

3 of 3 models pick Rongzhu.

Questions

The result 7 questions

Who wins, and how likely?

  • ChatGPT

    Rongzhu: 59% (about 59 in 100 fights). Garcia: 41%.

  • Claude

    Rongzhu: 58% (about 58 in 100 fights). Garcia: 42%.

  • Gemini

    Rongzhu: 56% (about 56 in 100 fights). Garcia: 44%.

What is the single most likely outcome?

  • ChatGPT

    Rongzhu by decision: 32% (about 32 in 100).

  • Claude

    Rongzhu by KO/TKO: 30% (about 30 in 100).

  • Gemini

    Rongzhu by decision: 36% (about 36 in 100).

What are the three most likely outcomes, and why?

  • ChatGPT

    1. Rongzhu by decision (32%); 2. Garcia by decision (25%); 3. Rongzhu by KO/TKO (22%)

  • Claude

    1. Rongzhu by KO/TKO (30%); 2. Garcia by decision (25%); 3. Rongzhu by decision (18%)

  • Gemini

    1. Rongzhu by decision (36%); 2. Garcia by decision (31%); 3. Rongzhu by KO/TKO (15%)

How confident is the model?

  • ChatGPT

    6 of 10, based on Rongzhu's 59% win chance.

  • Claude

    6 of 10, based on Rongzhu's 58% win chance.

  • Gemini

    6 of 10, based on Rongzhu's 56% win chance.

Does it end early or go to the judges?

  • ChatGPT

    Finish (KO/TKO or submission): 43%. Decision: 57%.

  • Claude

    Finish (KO/TKO or submission): 57%. Decision: 43%.

  • Gemini

    Finish (KO/TKO or submission): 33%. Decision: 67%.

How does Garcia win?

  • ChatGPT

    Garcia wins 41%: KO/TKO 7%, submission 9%, decision 25%.

  • Claude

    Garcia wins 42%: KO/TKO 10%, submission 7%, decision 25%.

  • Gemini

    Garcia wins 44%: KO/TKO 5%, submission 8%, decision 31%.

How does Rongzhu win?

  • ChatGPT

    Rongzhu wins 59%: KO/TKO 22%, submission 5%, decision 32%.

  • Claude

    Rongzhu wins 58%: KO/TKO 30%, submission 10%, decision 18%.

  • Gemini

    Rongzhu wins 56%: KO/TKO 15%, submission 5%, decision 36%.

What if 1 question

What is the upset path?

  • ChatGPT

    Garcia's most likely upset: Garcia by decision (25%).

  • Claude

    Garcia's most likely upset: Garcia by decision (25%).

  • Gemini

    Garcia's most likely upset: Garcia by decision (31%).

Compared with others 1 question

Do the models agree?

  • All models

    The models agree: all 3 pick Rongzhu.

After the fight 2 questions

What happened vs what the model said?

  • ChatGPT

    Result: Rongzhu by decision, the model's most likely outcome.

  • Claude

    Result: Rongzhu by decision, the model's number 3 outcome. Its most likely outcome was Rongzhu by KO/TKO (30%).

  • Gemini

    Result: Rongzhu by decision, the model's most likely outcome.

How much chance did it give the actual result?

  • ChatGPT

    32% (about 32 in 100).

  • Claude

    18% (about 18 in 100).

  • Gemini

    36% (about 36 in 100).

More questions (20)

The result 7 questions

KO/TKO vs submission vs decision overall

  • ChatGPT

    KO/TKO 29%, submission 14%, decision 57%.

  • Claude

    KO/TKO 40%, submission 17%, decision 43%.

  • Gemini

    KO/TKO 20%, submission 13%, decision 67%.

Who is more likely to finish the other?

  • ChatGPT

    Rongzhu: 27%, against 16% for Garcia.

  • Claude

    Rongzhu: 40%, against 17% for Garcia.

  • Gemini

    Rongzhu: 20%, against 13% for Garcia.

Can Garcia get the finish? Can Rongzhu?

  • ChatGPT

    Garcia: 16% (KO/TKO 7%, submission 9%). Rongzhu: 27% (KO/TKO 22%, submission 5%).

  • Claude

    Garcia: 17% (KO/TKO 10%, submission 7%). Rongzhu: 40% (KO/TKO 30%, submission 10%).

  • Gemini

    Garcia: 13% (KO/TKO 5%, submission 8%). Rongzhu: 20% (KO/TKO 15%, submission 5%).

Who is more likely to be knocked out, and who to be submitted?

  • ChatGPT

    Garcia is knocked out in 22% and submitted in 5%. Rongzhu is knocked out in 7% and submitted in 9%.

  • Claude

    Garcia is knocked out in 30% and submitted in 10%. Rongzhu is knocked out in 10% and submitted in 7%.

  • Gemini

    Garcia is knocked out in 15% and submitted in 5%. Rongzhu is knocked out in 5% and submitted in 8%.

How lopsided is this fight?

  • ChatGPT

    A clear favourite: 59% vs 41%.

  • Claude

    A clear favourite: 58% vs 42%.

  • Gemini

    A clear favourite: 56% vs 44%.

Each fighter's single most likely way to win

  • ChatGPT

    Garcia by decision: 25%. Rongzhu by decision: 32%.

  • Gemini

    Garcia by decision: 31%. Rongzhu by decision: 36%.

How big an upset would it be if the underdog wins?

  • ChatGPT

    Garcia wins 41% (about 1 in 2 fights): a modest upset.

  • Claude

    Garcia wins 42% (about 1 in 2 fights): a modest upset.

  • Gemini

    Garcia wins 44% (about 1 in 2 fights): a modest upset.

Timing 1 question

Chance it goes to a decision

  • ChatGPT

    57%.

  • Claude

    43%.

  • Gemini

    67%.

What if 1 question

If it goes to the judges, who wins?

  • ChatGPT

    If it goes to the judges: Garcia 44%, Rongzhu 56%.

  • Claude

    If it goes to the judges: Garcia 58%, Rongzhu 42%.

  • Gemini

    If it goes to the judges: Garcia 46%, Rongzhu 54%.

Compared with others 5 questions

Where does this model differ from the others?

  • ChatGPT

    Biggest difference: Rongzhu by decision, 32% here against 27% on average for the others.

  • Claude

    Biggest difference: Rongzhu by decision, 18% here against 34% on average for the others.

How does it compare with analyst picks?

  • ChatGPT

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (59%).

  • Claude

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (58%).

  • Gemini

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (56%).

Which model is most confident on Garcia, and which on Rongzhu?

  • All models

    On Garcia: Gemini (44%). On Rongzhu: ChatGPT (59%).

Where do the models disagree most?

  • All models

    Rongzhu by decision: from 18% (Claude) to 36% (Gemini).

Which analyst agrees most with this model?

  • ChatGPT

    TheWeasle (Rongzhu by decision), Bedtime MMA (Rongzhu by decision), DFS By The Numbers (Rongzhu by decision), Kunath (Rongzhu by decision), MMA Lock of the Night (Rongzhu by decision) and Jimbo Ortega MMA (Rongzhu by decision): the same winner and method as this model, tied; this model favours Rongzhu, most likely by decision.

  • Gemini

    TheWeasle (Rongzhu by decision), Bedtime MMA (Rongzhu by decision), DFS By The Numbers (Rongzhu by decision), Kunath (Rongzhu by decision), MMA Lock of the Night (Rongzhu by decision) and Jimbo Ortega MMA (Rongzhu by decision): the same winner and method as this model, tied; this model favours Rongzhu, 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 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

    Gemini, which gave the actual result 36%.

Was the actual result in this model's top 3?

  • All models

    Yes.

ChatGPT

Pick

Rongzhu

Confidence 6 of 10 · Medium

Most likely: Rongzhu by decision, about 32 in 100

Win chance: Garcia 41%, Rongzhu 59%.

Most likely outcomes

  1. Rongzhu by decision32%
  2. Garcia by decision25%
  3. Rongzhu by KO/TKO22%
How it ends
  1. KO/TKO: Garcia 7%, Rongzhu 22%.
  2. Submission: Garcia 9%, Rongzhu 5%.
  3. Decision: Garcia 25%, Rongzhu 32%.

Questions

The result 7 questions

Who wins, and how likely?

  • ChatGPT

    Rongzhu: 59% (about 59 in 100 fights). Garcia: 41%.

Other models' answers

  • Claude

    Rongzhu: 58% (about 58 in 100 fights). Garcia: 42%.

  • Gemini

    Rongzhu: 56% (about 56 in 100 fights). Garcia: 44%.

What is the single most likely outcome?

  • ChatGPT

    Rongzhu by decision: 32% (about 32 in 100).

Other models' answers

  • Claude

    Rongzhu by KO/TKO: 30% (about 30 in 100).

  • Gemini

    Rongzhu by decision: 36% (about 36 in 100).

What are the three most likely outcomes, and why?

  • ChatGPT

    1. Rongzhu by decision (32%); 2. Garcia by decision (25%); 3. Rongzhu by KO/TKO (22%)

Other models' answers

  • Claude

    1. Rongzhu by KO/TKO (30%); 2. Garcia by decision (25%); 3. Rongzhu by decision (18%)

  • Gemini

    1. Rongzhu by decision (36%); 2. Garcia by decision (31%); 3. Rongzhu by KO/TKO (15%)

How confident is the model?

  • ChatGPT

    6 of 10, based on Rongzhu's 59% win chance.

Other models' answers

  • Claude

    6 of 10, based on Rongzhu's 58% win chance.

  • Gemini

    6 of 10, based on Rongzhu's 56% win chance.

Does it end early or go to the judges?

  • ChatGPT

    Finish (KO/TKO or submission): 43%. Decision: 57%.

Other models' answers

  • Claude

    Finish (KO/TKO or submission): 57%. Decision: 43%.

  • Gemini

    Finish (KO/TKO or submission): 33%. Decision: 67%.

How does Garcia win?

  • ChatGPT

    Garcia wins 41%: KO/TKO 7%, submission 9%, decision 25%.

Other models' answers

  • Claude

    Garcia wins 42%: KO/TKO 10%, submission 7%, decision 25%.

  • Gemini

    Garcia wins 44%: KO/TKO 5%, submission 8%, decision 31%.

How does Rongzhu win?

  • ChatGPT

    Rongzhu wins 59%: KO/TKO 22%, submission 5%, decision 32%.

Other models' answers

  • Claude

    Rongzhu wins 58%: KO/TKO 30%, submission 10%, decision 18%.

  • Gemini

    Rongzhu wins 56%: KO/TKO 15%, submission 5%, decision 36%.

What if 1 question

What is the upset path?

  • ChatGPT

    Garcia's most likely upset: Garcia by decision (25%).

Other models' answers

  • Gemini

    Garcia's most likely upset: Garcia by decision (31%).

Compared with others 1 question

Do the models agree?

  • ChatGPT

    The models agree: all 3 pick Rongzhu.

After the fight 2 questions

What happened vs what the model said?

  • ChatGPT

    Result: Rongzhu by decision, the model's most likely outcome.

Other models' answers

  • Claude

    Result: Rongzhu by decision, the model's number 3 outcome. Its most likely outcome was Rongzhu by KO/TKO (30%).

How much chance did it give the actual result?

  • ChatGPT

    32% (about 32 in 100).

Other models' answers

  • Claude

    18% (about 18 in 100).

  • Gemini

    36% (about 36 in 100).

More questions (20)

The result 7 questions

KO/TKO vs submission vs decision overall

  • ChatGPT

    KO/TKO 29%, submission 14%, decision 57%.

Other models' answers

  • Claude

    KO/TKO 40%, submission 17%, decision 43%.

  • Gemini

    KO/TKO 20%, submission 13%, decision 67%.

Who is more likely to finish the other?

  • ChatGPT

    Rongzhu: 27%, against 16% for Garcia.

Other models' answers

  • Claude

    Rongzhu: 40%, against 17% for Garcia.

  • Gemini

    Rongzhu: 20%, against 13% for Garcia.

Can Garcia get the finish? Can Rongzhu?

  • ChatGPT

    Garcia: 16% (KO/TKO 7%, submission 9%). Rongzhu: 27% (KO/TKO 22%, submission 5%).

Other models' answers

  • Claude

    Garcia: 17% (KO/TKO 10%, submission 7%). Rongzhu: 40% (KO/TKO 30%, submission 10%).

  • Gemini

    Garcia: 13% (KO/TKO 5%, submission 8%). Rongzhu: 20% (KO/TKO 15%, submission 5%).

Who is more likely to be knocked out, and who to be submitted?

  • ChatGPT

    Garcia is knocked out in 22% and submitted in 5%. Rongzhu is knocked out in 7% and submitted in 9%.

Other models' answers

  • Claude

    Garcia is knocked out in 30% and submitted in 10%. Rongzhu is knocked out in 10% and submitted in 7%.

  • Gemini

    Garcia is knocked out in 15% and submitted in 5%. Rongzhu is knocked out in 5% and submitted in 8%.

How lopsided is this fight?

  • ChatGPT

    A clear favourite: 59% vs 41%.

Other models' answers

  • Claude

    A clear favourite: 58% vs 42%.

  • Gemini

    A clear favourite: 56% vs 44%.

Each fighter's single most likely way to win

  • ChatGPT

    Garcia by decision: 25%. Rongzhu by decision: 32%.

Other models' answers

  • Gemini

    Garcia by decision: 31%. Rongzhu by decision: 36%.

How big an upset would it be if the underdog wins?

  • ChatGPT

    Garcia wins 41% (about 1 in 2 fights): a modest upset.

Other models' answers

  • Claude

    Garcia wins 42% (about 1 in 2 fights): a modest upset.

  • Gemini

    Garcia wins 44% (about 1 in 2 fights): a modest upset.

Timing 1 question

Chance it goes to a decision

  • ChatGPT

    57%.

Other models' answers

  • Claude

    43%.

  • Gemini

    67%.

What if 1 question

If it goes to the judges, who wins?

  • ChatGPT

    If it goes to the judges: Garcia 44%, Rongzhu 56%.

Other models' answers

  • Claude

    If it goes to the judges: Garcia 58%, Rongzhu 42%.

  • Gemini

    If it goes to the judges: Garcia 46%, Rongzhu 54%.

Compared with others 5 questions

Where does this model differ from the others?

  • ChatGPT

    Biggest difference: Rongzhu by decision, 32% here against 27% on average for the others.

Other models' answers

  • Claude

    Biggest difference: Rongzhu by decision, 18% here against 34% on average for the others.

How does it compare with analyst picks?

  • ChatGPT

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (59%).

Other models' answers

  • Claude

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (58%).

  • Gemini

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (56%).

Which model is most confident on Garcia, and which on Rongzhu?

  • ChatGPT

    On Garcia: Gemini (44%). On Rongzhu: ChatGPT (59%).

Where do the models disagree most?

  • ChatGPT

    Rongzhu by decision: from 18% (Claude) to 36% (Gemini).

Which analyst agrees most with this model?

  • ChatGPT

    TheWeasle (Rongzhu by decision), Bedtime MMA (Rongzhu by decision), DFS By The Numbers (Rongzhu by decision), Kunath (Rongzhu by decision), MMA Lock of the Night (Rongzhu by decision) and Jimbo Ortega MMA (Rongzhu by decision): the same winner and method as this model, tied; this model favours Rongzhu, 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.

Other models' answers

  • Claude

    On 5 Sep 2026, by claude-sonnet-5.

  • Gemini

    On 5 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

    Gemini, which gave the actual result 36%.

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

Rongzhu

Confidence 6 of 10 · Medium

Most likely: Rongzhu by KO/TKO, about 30 in 100

The model's predicted finish round: 2.

Win chance: Garcia 42%, Rongzhu 58%.

Most likely outcomes

  1. Rongzhu by KO/TKO30%
  2. Garcia by decision25%
  3. Rongzhu by decision18%
How it ends
  1. KO/TKO: Garcia 10%, Rongzhu 30%.
  2. Submission: Garcia 7%, Rongzhu 10%.
  3. Decision: Garcia 25%, Rongzhu 18%.

Questions

The result 7 questions

Who wins, and how likely?

  • Claude

    Rongzhu: 58% (about 58 in 100 fights). Garcia: 42%.

Other models' answers

  • ChatGPT

    Rongzhu: 59% (about 59 in 100 fights). Garcia: 41%.

  • Gemini

    Rongzhu: 56% (about 56 in 100 fights). Garcia: 44%.

What is the single most likely outcome?

  • Claude

    Rongzhu by KO/TKO: 30% (about 30 in 100).

Other models' answers

  • ChatGPT

    Rongzhu by decision: 32% (about 32 in 100).

  • Gemini

    Rongzhu by decision: 36% (about 36 in 100).

What are the three most likely outcomes, and why?

  • Claude

    1. Rongzhu by KO/TKO (30%); 2. Garcia by decision (25%); 3. Rongzhu by decision (18%)

Other models' answers

  • ChatGPT

    1. Rongzhu by decision (32%); 2. Garcia by decision (25%); 3. Rongzhu by KO/TKO (22%)

  • Gemini

    1. Rongzhu by decision (36%); 2. Garcia by decision (31%); 3. Rongzhu by KO/TKO (15%)

How confident is the model?

  • Claude

    6 of 10, based on Rongzhu's 58% win chance.

Other models' answers

  • ChatGPT

    6 of 10, based on Rongzhu's 59% win chance.

  • Gemini

    6 of 10, based on Rongzhu's 56% win chance.

Does it end early or go to the judges?

  • Claude

    Finish (KO/TKO or submission): 57%. Decision: 43%.

Other models' answers

  • ChatGPT

    Finish (KO/TKO or submission): 43%. Decision: 57%.

  • Gemini

    Finish (KO/TKO or submission): 33%. Decision: 67%.

How does Garcia win?

  • Claude

    Garcia wins 42%: KO/TKO 10%, submission 7%, decision 25%.

Other models' answers

  • ChatGPT

    Garcia wins 41%: KO/TKO 7%, submission 9%, decision 25%.

  • Gemini

    Garcia wins 44%: KO/TKO 5%, submission 8%, decision 31%.

How does Rongzhu win?

  • Claude

    Rongzhu wins 58%: KO/TKO 30%, submission 10%, decision 18%.

Other models' answers

  • ChatGPT

    Rongzhu wins 59%: KO/TKO 22%, submission 5%, decision 32%.

  • Gemini

    Rongzhu wins 56%: KO/TKO 15%, submission 5%, decision 36%.

What if 1 question

What is the upset path?

  • Claude

    Garcia's most likely upset: Garcia by decision (25%).

Other models' answers

  • Gemini

    Garcia's most likely upset: Garcia by decision (31%).

Compared with others 1 question

Do the models agree?

  • Claude

    The models agree: all 3 pick Rongzhu.

After the fight 2 questions

What happened vs what the model said?

  • Claude

    Result: Rongzhu by decision, the model's number 3 outcome. Its most likely outcome was Rongzhu by KO/TKO (30%).

Other models' answers

  • ChatGPT

    Result: Rongzhu by decision, the model's most likely outcome.

  • Gemini

    Result: Rongzhu by decision, the model's most likely outcome.

How much chance did it give the actual result?

  • Claude

    18% (about 18 in 100).

Other models' answers

  • ChatGPT

    32% (about 32 in 100).

  • Gemini

    36% (about 36 in 100).

More questions (18)

The result 6 questions

KO/TKO vs submission vs decision overall

  • Claude

    KO/TKO 40%, submission 17%, decision 43%.

Other models' answers

  • ChatGPT

    KO/TKO 29%, submission 14%, decision 57%.

  • Gemini

    KO/TKO 20%, submission 13%, decision 67%.

Who is more likely to finish the other?

  • Claude

    Rongzhu: 40%, against 17% for Garcia.

Other models' answers

  • ChatGPT

    Rongzhu: 27%, against 16% for Garcia.

  • Gemini

    Rongzhu: 20%, against 13% for Garcia.

Can Garcia get the finish? Can Rongzhu?

  • Claude

    Garcia: 17% (KO/TKO 10%, submission 7%). Rongzhu: 40% (KO/TKO 30%, submission 10%).

Other models' answers

  • ChatGPT

    Garcia: 16% (KO/TKO 7%, submission 9%). Rongzhu: 27% (KO/TKO 22%, submission 5%).

  • Gemini

    Garcia: 13% (KO/TKO 5%, submission 8%). Rongzhu: 20% (KO/TKO 15%, submission 5%).

Who is more likely to be knocked out, and who to be submitted?

  • Claude

    Garcia is knocked out in 30% and submitted in 10%. Rongzhu is knocked out in 10% and submitted in 7%.

Other models' answers

  • ChatGPT

    Garcia is knocked out in 22% and submitted in 5%. Rongzhu is knocked out in 7% and submitted in 9%.

  • Gemini

    Garcia is knocked out in 15% and submitted in 5%. Rongzhu is knocked out in 5% and submitted in 8%.

How lopsided is this fight?

  • Claude

    A clear favourite: 58% vs 42%.

Other models' answers

  • ChatGPT

    A clear favourite: 59% vs 41%.

  • Gemini

    A clear favourite: 56% vs 44%.

How big an upset would it be if the underdog wins?

  • Claude

    Garcia wins 42% (about 1 in 2 fights): a modest upset.

Other models' answers

  • ChatGPT

    Garcia wins 41% (about 1 in 2 fights): a modest upset.

  • Gemini

    Garcia wins 44% (about 1 in 2 fights): a modest upset.

Timing 1 question

Chance it goes to a decision

  • Claude

    43%.

Other models' answers

  • ChatGPT

    57%.

  • Gemini

    67%.

What if 1 question

If it goes to the judges, who wins?

  • Claude

    If it goes to the judges: Garcia 58%, Rongzhu 42%.

Other models' answers

  • ChatGPT

    If it goes to the judges: Garcia 44%, Rongzhu 56%.

  • Gemini

    If it goes to the judges: Garcia 46%, Rongzhu 54%.

Compared with others 4 questions

Where does this model differ from the others?

  • Claude

    Biggest difference: Rongzhu by decision, 18% here against 34% on average for the others.

Other models' answers

  • ChatGPT

    Biggest difference: Rongzhu by decision, 32% here against 27% on average for the others.

How does it compare with analyst picks?

  • Claude

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (58%).

Other models' answers

  • ChatGPT

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (59%).

  • Gemini

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (56%).

Which model is most confident on Garcia, and which on Rongzhu?

  • Claude

    On Garcia: Gemini (44%). On Rongzhu: ChatGPT (59%).

Where do the models disagree most?

  • Claude

    Rongzhu by decision: from 18% (Claude) to 36% (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 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

    Gemini, which gave the actual result 36%.

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

Rongzhu

Confidence 6 of 10 · Medium

Most likely: Rongzhu by decision, about 36 in 100

Win chance: Garcia 44%, Rongzhu 56%.

Most likely outcomes

  1. Rongzhu by decision36%
  2. Garcia by decision31%
  3. Rongzhu by KO/TKO15%
How it ends
  1. KO/TKO: Garcia 5%, Rongzhu 15%.
  2. Submission: Garcia 8%, Rongzhu 5%.
  3. Decision: Garcia 31%, Rongzhu 36%.

Questions

The result 7 questions

Who wins, and how likely?

  • Gemini

    Rongzhu: 56% (about 56 in 100 fights). Garcia: 44%.

Other models' answers

  • ChatGPT

    Rongzhu: 59% (about 59 in 100 fights). Garcia: 41%.

  • Claude

    Rongzhu: 58% (about 58 in 100 fights). Garcia: 42%.

What is the single most likely outcome?

  • Gemini

    Rongzhu by decision: 36% (about 36 in 100).

Other models' answers

  • ChatGPT

    Rongzhu by decision: 32% (about 32 in 100).

  • Claude

    Rongzhu by KO/TKO: 30% (about 30 in 100).

What are the three most likely outcomes, and why?

  • Gemini

    1. Rongzhu by decision (36%); 2. Garcia by decision (31%); 3. Rongzhu by KO/TKO (15%)

Other models' answers

  • ChatGPT

    1. Rongzhu by decision (32%); 2. Garcia by decision (25%); 3. Rongzhu by KO/TKO (22%)

  • Claude

    1. Rongzhu by KO/TKO (30%); 2. Garcia by decision (25%); 3. Rongzhu by decision (18%)

How confident is the model?

  • Gemini

    6 of 10, based on Rongzhu's 56% win chance.

Other models' answers

  • ChatGPT

    6 of 10, based on Rongzhu's 59% win chance.

  • Claude

    6 of 10, based on Rongzhu's 58% win chance.

Does it end early or go to the judges?

  • Gemini

    Finish (KO/TKO or submission): 33%. Decision: 67%.

Other models' answers

  • ChatGPT

    Finish (KO/TKO or submission): 43%. Decision: 57%.

  • Claude

    Finish (KO/TKO or submission): 57%. Decision: 43%.

How does Garcia win?

  • Gemini

    Garcia wins 44%: KO/TKO 5%, submission 8%, decision 31%.

Other models' answers

  • ChatGPT

    Garcia wins 41%: KO/TKO 7%, submission 9%, decision 25%.

  • Claude

    Garcia wins 42%: KO/TKO 10%, submission 7%, decision 25%.

How does Rongzhu win?

  • Gemini

    Rongzhu wins 56%: KO/TKO 15%, submission 5%, decision 36%.

Other models' answers

  • ChatGPT

    Rongzhu wins 59%: KO/TKO 22%, submission 5%, decision 32%.

  • Claude

    Rongzhu wins 58%: KO/TKO 30%, submission 10%, decision 18%.

What if 1 question

What is the upset path?

  • Gemini

    Garcia's most likely upset: Garcia by decision (31%).

Other models' answers

  • ChatGPT

    Garcia's most likely upset: Garcia by decision (25%).

  • Claude

    Garcia's most likely upset: Garcia by decision (25%).

Compared with others 1 question

Do the models agree?

  • Gemini

    The models agree: all 3 pick Rongzhu.

After the fight 2 questions

What happened vs what the model said?

  • Gemini

    Result: Rongzhu by decision, the model's most likely outcome.

Other models' answers

  • Claude

    Result: Rongzhu by decision, the model's number 3 outcome. Its most likely outcome was Rongzhu by KO/TKO (30%).

How much chance did it give the actual result?

  • Gemini

    36% (about 36 in 100).

Other models' answers

  • ChatGPT

    32% (about 32 in 100).

  • Claude

    18% (about 18 in 100).

More questions (19)

The result 7 questions

KO/TKO vs submission vs decision overall

  • Gemini

    KO/TKO 20%, submission 13%, decision 67%.

Other models' answers

  • ChatGPT

    KO/TKO 29%, submission 14%, decision 57%.

  • Claude

    KO/TKO 40%, submission 17%, decision 43%.

Who is more likely to finish the other?

  • Gemini

    Rongzhu: 20%, against 13% for Garcia.

Other models' answers

  • ChatGPT

    Rongzhu: 27%, against 16% for Garcia.

  • Claude

    Rongzhu: 40%, against 17% for Garcia.

Can Garcia get the finish? Can Rongzhu?

  • Gemini

    Garcia: 13% (KO/TKO 5%, submission 8%). Rongzhu: 20% (KO/TKO 15%, submission 5%).

Other models' answers

  • ChatGPT

    Garcia: 16% (KO/TKO 7%, submission 9%). Rongzhu: 27% (KO/TKO 22%, submission 5%).

  • Claude

    Garcia: 17% (KO/TKO 10%, submission 7%). Rongzhu: 40% (KO/TKO 30%, submission 10%).

Who is more likely to be knocked out, and who to be submitted?

  • Gemini

    Garcia is knocked out in 15% and submitted in 5%. Rongzhu is knocked out in 5% and submitted in 8%.

Other models' answers

  • ChatGPT

    Garcia is knocked out in 22% and submitted in 5%. Rongzhu is knocked out in 7% and submitted in 9%.

  • Claude

    Garcia is knocked out in 30% and submitted in 10%. Rongzhu is knocked out in 10% and submitted in 7%.

How lopsided is this fight?

  • Gemini

    A clear favourite: 56% vs 44%.

Other models' answers

  • ChatGPT

    A clear favourite: 59% vs 41%.

  • Claude

    A clear favourite: 58% vs 42%.

Each fighter's single most likely way to win

  • Gemini

    Garcia by decision: 31%. Rongzhu by decision: 36%.

Other models' answers

  • ChatGPT

    Garcia by decision: 25%. Rongzhu by decision: 32%.

How big an upset would it be if the underdog wins?

  • Gemini

    Garcia wins 44% (about 1 in 2 fights): a modest upset.

Other models' answers

  • ChatGPT

    Garcia wins 41% (about 1 in 2 fights): a modest upset.

  • Claude

    Garcia wins 42% (about 1 in 2 fights): a modest upset.

Timing 1 question

Chance it goes to a decision

  • Gemini

    67%.

Other models' answers

  • ChatGPT

    57%.

  • Claude

    43%.

What if 1 question

If it goes to the judges, who wins?

  • Gemini

    If it goes to the judges: Garcia 46%, Rongzhu 54%.

Other models' answers

  • ChatGPT

    If it goes to the judges: Garcia 44%, Rongzhu 56%.

  • Claude

    If it goes to the judges: Garcia 58%, Rongzhu 42%.

Compared with others 4 questions

How does it compare with analyst picks?

  • Gemini

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (56%).

Other models' answers

  • ChatGPT

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (59%).

  • Claude

    Of 12 analyst picks, 3 back Garcia and 9 back Rongzhu. This model picks Rongzhu (58%).

Which model is most confident on Garcia, and which on Rongzhu?

  • Gemini

    On Garcia: Gemini (44%). On Rongzhu: ChatGPT (59%).

Where do the models disagree most?

  • Gemini

    Rongzhu by decision: from 18% (Claude) to 36% (Gemini).

Which analyst agrees most with this model?

  • Gemini

    TheWeasle (Rongzhu by decision), Bedtime MMA (Rongzhu by decision), DFS By The Numbers (Rongzhu by decision), Kunath (Rongzhu by decision), MMA Lock of the Night (Rongzhu by decision) and Jimbo Ortega MMA (Rongzhu by decision): the same winner and method as this model, tied; this model favours Rongzhu, most likely by decision.

How sure 4 questions

When was this forecast made, and by which model version?

  • Gemini

    On 5 Sep 2026, by a model version the provider did not report.

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 2 questions

Which model was closest?

  • Gemini

    Gemini, which gave the actual result 36%.

Was the actual result in this model's top 3?

  • Gemini

    Yes.

Version not reported · 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

No current consensus line is saved on this page.

Not betting advice · 21+. Gambling problem? Call 1-800-MY-RESET

Independent fan-made fight recap. Not affiliated with, endorsed by, or sponsored by the UFC or any other MMA promotion. Analysis is editorial opinion, not betting advice. Fighter names and records are used for commentary. Image credits · Methodology · Privacy · Terms.