Events · Saturday, 5 December 2026

UFC Fight Night

4 of 12 bouts called — 8 left alone, for a debut, a late replacement or too thin a record. We expect 2 to end inside the distance. Frozen and locked — and scored once the card is fought.

The card

5 December · locked
Middleweight Bout01 / 12
Israel Adesanya#9 MiddleweightElusive Finisher
Loss4
Pow84
Vol69
Acc67
SDf70
TDs0
Con1
Sub5
GDf67
Exp99
Shara Magomedov#15 MiddleweightRelentless Marksman
2Wins
Pow60
Vol92
Acc100
SDf30
TDs2
Con2
Sub8
GDf61
Exp58

38% to end inside the distance — by knockout if it does, 50% in round one.

Welterweight Bout02 / 12
Ian Machado Garry#1 WelterweightRelentless Marksman
Pow66
Vol75
Acc93
SDf57
TDs25
Con22
Sub23
GDf61
Exp85
Yaroslav Amosov#11Unranked

No card yet — a rate needs three UFC bouts before it means anything.

Left alone — no-stats

Heavyweight Bout03 / 12
Serghei Spivac#10 HeavyweightHunting Wrestler
Pow43
Vol42
Acc37
SDf48
TDs93
Con75
Sub86
GDf60
Exp79
Mario PintoHeavyweightSuffocating Marksman
4Wins
Pow75
Vol47
Acc95
SDf89
TDs94
Con95
Sub70
GDf95
Exp21

Strong call

57% to end inside the distance — by knockout if it does, 52% in round one.

Welterweight Bout04 / 12
Levan ChokheliUnranked

No card yet — a rate needs three UFC bouts before it means anything.

Islam DulatovUnranked

No card yet — a rate needs three UFC bouts before it means anything.

Left alone — no-stats

Lightweight Bout05 / 12
mairon santos alvesUnranked

No card yet — a rate needs three UFC bouts before it means anything.

akbar abdullaevUnranked

No card yet — a rate needs three UFC bouts before it means anything.

Left alone — debut

Light Heavyweight Bout06 / 12
Magomed TuchalovUnranked

No card yet — a rate needs three UFC bouts before it means anything.

Ion CutelabaLight HeavyweightHunting Wrestler
Pow57
Vol68
Acc19
SDf28
TDs96
Con64
Sub76
GDf33
Exp81

Left alone — no-stats

Flyweight Bout07 / 12
Bruno SilvaFlyweightPrecision Finisher
Loss2
Pow92
Vol67
Acc86
SDf20
TDs68
Con60
Sub67
GDf83
Exp74
Jafel FilhoBantamweightSuffocating Hunter
Pow15
Vol6
Acc34
SDf38
TDs73
Con80
Sub99
GDf15
Exp37

58% to end inside the distance, 47% in round one.

Light Heavyweight Bout08 / 12
Uran SatybaldievUnranked

No card yet — a rate needs three UFC bouts before it means anything.

ivan gnizditskiyUnranked

No card yet — a rate needs three UFC bouts before it means anything.

Left alone — debut

Middleweight Bout09 / 12
Marco TulioMiddleweightPrecision Machine
Loss2
Pow86
Vol98
Acc90
SDf36
TDs40
Con31
Sub33
GDf43
Exp14
JunYong ParkMiddleweightPrecision Hunter
Pow2
Vol82
Acc85
SDf53
TDs63
Con79
Sub86
GDf9
Exp76

Slight lean

52% to end inside the distance, 56% in round one.

Bantamweight Bout10 / 12
Pavel AndruscaUnranked

No card yet — a rate needs three UFC bouts before it means anything.

Mahammadali OsmanliUnranked

No card yet — a rate needs three UFC bouts before it means anything.

Left alone — no-stats

Middleweight Bout11 / 12
modestino rodriguesUnranked

No card yet — a rate needs three UFC bouts before it means anything.

Left alone — debut

Bantamweight Bout12 / 12
Abdul HusseinUnranked

No card yet — a rate needs three UFC bouts before it means anything.

Hecher SosaUnranked

No card yet — a rate needs three UFC bouts before it means anything.

Left alone — no-stats

Frozen before the card. If a fighter is replaced after this point the prediction is void rather than re-pointed. The winner call carries weaker evidence than the finish call throughout — it does not beat a one-line rule on accuracy, which is why its dots are muted.

What these divisions usually do

since 2015 · not a prediction
Light Heavyweight411 fights
Heavyweight417 fights
Middleweight650 fights
Welterweight790 fights
Lightweight834 fights
Bantamweight602 fights
Flyweight339 fights

How this works, and what it cannot do

Every fighter carries a profile built only from fights that had already happened when the prediction was made — never their career averages, which would contain the result being predicted. The models are refitted for each card against everything before that date.

“Will it finish?” is the claim worth reading. Tested on a held-out window it reached 60.7% against a 52% baseline, and its probabilities are well calibrated: fights called at 60–70% finished 68.5% of the time.

“Who wins?” is weak, and we would rather say so. On the same test it reached 62.6% — which is not statistically distinguishable from simply picking the fighter with the better UFC win rate. It is published for the record, not because it is clever.

Knockout or submission, we say only sometimes. Across all finishes the model is barely better than each division’s own knockout share and is worse on accuracy, so a probability printed on every bout would be meaningless. Above 75% confidence it earns its place: on the finishes it flags, the real knockout rate ran 8 to 14 points clear of what the division alone predicts, in every one of five walk-forward test windows, covering about a quarter of finishes. The call appears on those bouts and nowhere else.

It almost never calls a submission, and that is the finding rather than a gap. Not one bout in the held-out window reached 75% that way. A knockout is written into two fighters’ careers long before the cage door shuts; a submission tends to come out of a scramble no record predicts. Every bout still shows its division’s historical mix, which is context and not a claim.

It has no concept of who a fighter has beaten. A dominant champion and a fighter with the same record against far weaker opposition look identical to it, which is the single biggest thing missing and the next thing we will add.

Where a fighter is making their UFC debut, is a late replacement, or has too few fights with statistics, we publish no prediction at all rather than guess. Those bouts are shown as abstentions.

This exists to answer a question about data, not to help anyone gamble. We publish no odds, make no comparison to bookmakers’ lines, and none of it should be used to stake money. The insight stories explain the analysis these models are built from.