Surest 1 in 4 calls
71.1% Engine online · calibrated for UFC
Powered by theTESUJIprediction engine
Most predictions ask for your trust and show you nothing. This one shows its work. Every fight gets a win probability, the chances of each method, and a finish timing, read from the fighters' own numbers, and opens up so you can check the reasoning yourself.
All 2,933 fights
61.1%Confidence cap
85%Main event
Lightweight · 5 rounds
Renato
Moicano
Moicano
13-7 UFC
20 fights · 188 min
20 fights · 188 min
Tom
Nolan
Nolan
5-1 UFC
6 fights · 54 min, a short UFC history
6 fights · 54 min, a short UFC history
Strikes / minMoicano: 4.1Nolan: 4.7 — ahead by 0.6
Absorbed / minlower winsMoicano: 3.5 — ahead by 0.3Nolan: 3.8
AccuracyMoicano: 49% — ahead by 4Nolan: 45%
Takedowns / 15 minMoicano: 1.7 — ahead by 0.6Nolan: 1.1
Takedown defenseMoicano: 64% — ahead by 6Nolan: 58%
Finish rateMoicano: 69% — ahead by 29Nolan: 40%
Inside the app
Events
Rankings
Odds board
Predictions
All fighters
Head-to-head
01 / Schedule
Events
Full fight cards, main to early prelims, with live schedules and results.
Open EventsHow it works
Most UFC picks are sold as locks. TESUJI does the opposite: it gives you the honest probability of each outcome — and shows exactly how it got there — so you can read the fight for yourself.
Its own read, not the market's
The number comes from the fighters' own record, output and durability — not from the betting line. The market is shown beside it so you can see where the two disagree.
Calibrated, not cocky
Probabilities stay honest — nothing here is ever a lock. A 60% pick is a 60% pick, and the record shows how those have actually landed.
It shows its work
Win, method, and — when both fighters have the UFC record to earn it — a specific round, each with the reasoning behind it. On the rest it says so rather than guessing. That engine is TESUJI.
And it's kept honest: every card is locked before the fights and graded in public, wins and losses alike. See the track record →
Does it actually work?
Tested against history
61.1%
of winners called across 2,933 past fights, each predicted using only what was known before the fight.
Both bars share one scale that starts at 40%, not zero. The pale mark is a coin flip at 50%, the number to beat. UFC fights only: the engine learned from older fights, then was tested on newer ones it had never seen.
What this test leaves out
- Elo ratings. There is no fight-by-fight record of them, so the test ran without them. The live site runs without them too.
- Scheduled rounds. They aren't recorded, so every fight is scored as a three-rounder.
- The oldest 40% of fights. The engine learned from them, so they are never graded.
- Draws and no contests. There's no winner to call.
- Fighters with fewer than two earlier UFC fights. There's too little to read.
This is the engine the site runs, reading the same fight history.