Skip to content
CageFrame: AI fight predictions for UFC fans
Next cardBuckley vs. Malott · Sat, Oct 17

Predict every UFC fight before it starts.

The world's first AI fight analyst.

Create your free account

  • The model's win probability and the factors behind it
  • A written breakdown of every fight on the next cards
  • Every UFC fighter's record and career stats

Accounts open very soon.

+42K satisfied users

Champion · Featherweight title · UFC 333

1,574 hours

of UFC fights since 1993: all 8,943 of them

4,196 fighters

every athlete on UFC.com, read in

Introducing

Prometheus

The CageFrame model. One rating per fighter, seven factors, one win probability.

How it works

One desk. Everything about the fight.

From the card to the cage door, here's how the fight desk turns the numbers into a read on every fight.

1/4

Every fight on the next cards, one tap away

22 fights across 10 weight classes: pick any bout on the next UFC cards, from the main event to the first prelim, by card or by division.

2/4

Both fighters, side by side

Records, size, reach, age, the last five fights and every career average, lined up on one screen so the differences jump out. Official numbers only.

3/4

Prometheus reads the matchup

The model's win probability and the factors that move it, then a written breakdown: the key edges, how each fighter wins, what to watch in the cage.

4/4

Ask anything about the fight

Type a question, get a short answer from the fight's own numbers, with its sources.

Reviews

They liked us.

Ultra

My coach kept telling me my right hand drops after the jab. Seeing the same thing broken down in pro fights is what finally made it click. Now I bring the breakdowns to practice.

Ryan M.

Amateur MMA fighter

Pro

I watch the prelims too, and half the time I don’t know either guy. Ten minutes on CageFrame and I actually have something to look for in every fight.

Alex D.

Watches every card

Ultra

We use it to prep game plans. A recurring opening is a concrete topic for training, and I can keep asking follow-ups until I know how we’d exploit it.

Marcus T.

MMA coach

Starter

I don’t need a dossier on everyone. I pick the fights I care about, read the breakdown, done. Starter is exactly enough for me.

Sophie L.

Follows a few fighters

Ultra

Six weeks out, I pulled up my opponent’s patterns. He shoots every time he gets backed onto the fence. We drilled the sprawl-and-pivot all camp and it played out exactly like that.

Jordan P.

Pro MMA fighter, 7–2

Ultra

The win probability is nice, but the sequence is the useful part: what triggers the habit, where the opening is, how you’d counter it. I rewatch my own rounds differently now.

Daniel R.

Kickboxer

Pro

I always look at the grappling side first. Takedown numbers next to the defensive stats tell me pretty fast whether someone can keep it standing.

Leila B.

BJJ purple belt

Pro

Our card previews used to be gut picks. Now we show up with numbers we can check and two or three ways each fight could go. The episodes got way better.

Chris W.

MMA podcast host

Ultra

When one of my guys gets a fight, I paste the opponent’s fight links and wait for the breakdown. It flags the habits I’d have found after hours of tape, and we build the game plan from there.

Tomás V.

Head coach, MMA gym

Starter

I used to judge a fight by the records. Reach, recent opponents, habits: now I get why two 12–2 guys can be a completely lopsided matchup.

Omar K.

Fan since 2019

Illustrative reviews.

Pricing

Read every fight like a coach.

Every plan includes the fighter stats and Prometheus's win probability. Pick how many full AI breakdowns you want.

Starter

Full AI breakdowns for the fights you follow most.

$12.99per month

  • Stats, comparisons and win probability
  • 5 full AI analyses a month
  • Patterns and weaknesses
  • 10 Ask CageFrame questions a month
Most popular

Pro

Every fight on CageFrame, fully broken down.

$24.99per month

  • Stats, comparisons and win probability
  • All published AI analysesRead every available fight dossier
  • Patterns and weaknesses
  • Victory scenarios
  • Sourced fight-week news
  • 75 Ask CageFrame questions a month

Ultra

Every published fight analysis, with more room to ask.

$99per month

  • Stats, comparisons and win probability
  • All published AI analysesRead every available fight dossier
  • Patterns and weaknesses
  • Victory scenarios
  • Sourced fight-week news
  • 200 Ask CageFrame questions a month
Compare every feature
What each plan includes
Starter, $12.99 a monthPro, $24.99 a monthUltra, $99 a month
Fighter stats and comparisons
IncludedIncludedIncluded
Model win probability
IncludedIncludedIncluded
Full AI analysesOne fight each, open until after its event
5 a monthUnlimitedUnlimited
Patterns and weaknesses
IncludedIncludedIncluded
Victory scenarios
Not includedIncludedIncluded
Sourced fight-week news
Not includedIncludedIncluded
Ask CageFrame questions
10 a month75 a month200 a month
FAQ

Frequent questions

A clear answer to all your questions about CageFrame.

1.Is CageFrame a betting site?

No. CageFrame is fight analysis for fans: no wagers, no deposits, no betting accounts, no odds.

2.How are the win probabilities made?

Each "Model win probability" is set by a statistical model. The AI only writes the matchup text around it and never sets a number. The model rates every fighter from all UFC results on Wikipedia since 1993 (a Glicko-2 rating), then weighs that rating with age, reach, time since the last fight, UFC experience, current streak and the strength of recent opponents. It was fitted on 2005–2014 fights, its settings were chosen on 2015–2020 fights, and it was then tested on 2,968 UFC fights with a winner since 2021, none of which it was trained or tuned on. That test period has been scored three times, so its pass is weaker evidence than a single look (the credits page lists each scoring); the real check is the ledger of numbers frozen before each fight. It learned from Wikipedia and Wikidata only. For a fighter on the next cards whose date of birth or reach is missing there, or disagrees with our hand-checked card data, it uses the card value, and the fight page says so (with no value anywhere, it uses the division average and flags that too). Each percentage is the chance of winning if the fight has a winner. It is frozen before the fight in an append-only ledger: a correction is a new entry, and the fight page still lists the number it replaced, under "Sources and versions". When the whole percentages read 50/50, neither fighter is picked. It doesn't use striking or grappling stats (there's no licensed fight-by-fight history of them) or betting odds. When two fighters both make their UFC debut there isn't enough history, so there's no number.

3.Where does the data come from?

Records and career averages come from UFC.com athlete profiles and UFC's event data, cross-checked against Wikipedia, Sherdog and ESPN. Every fighter profile links to its exact sources.

4.Which fights are covered?

Every bout on the next UFC cards: UFC Fight Night Buckley vs. Malott (Sat, Oct 17, 13 fights) and UFC 333 Volkanovski vs. Evloev (Sat, Oct 24, 9 fights).

5.Which fighters can I look up?

All 4,196 athletes with a UFC.com profile, active or not, with their record, ranking, career stats and latest UFC fights as UFC.com publishes them. Fighters on the next cards get a deeper, cross-checked profile.

6.Is CageFrame affiliated with the UFC?

No. CageFrame is independent and is not affiliated with, endorsed by or sponsored by the UFC, Zuffa or TKO.

The next fight starts here.

Every fight on the next cards, broken down before the first bell.

See analysis