UFC 327: Predictions & Analysis
UFC 327 lands on Saturday, April 11, 2026 in Miami, Florida, USA with 8 bouts on the card. Below is our fight-by-fight breakdown, combining Elo ratings, rolling statistical trends, style matchup data, and betting market context into a pick for every bout.
Quick Picks
| Matchup | Pick | Confidence | Prob |
|---|---|---|---|
| Joshua Van vs Tatsuro TairaFlyweight | Joshua Van | Toss-up | 52% |
| Kevin Holland vs Randy BrownWelterweight | Randy Brown | Lean | 60% |
| Tatiana Suarez vs Loopy GodinezWomen's Strawweight | Tatiana Suarez | Lean | 58% |
| Curtis Blaydes vs Josh HokitHeavyweight | Curtis Blaydes | Lean | 64% |
| Dominick Reyes vs Johnny WalkerLight Heavyweight | Johnny Walker | Toss-up | 54% |
| Azamat Murzakanov vs Paulo CostaLight Heavyweight | Azamat Murzakanov | Toss-up | 53% |
| Cub Swanson vs Nate LandwehrFeatherweight | Cub Swanson | Toss-up | 54% |
| Kyle Daukaus vs Vicente LuqueMiddleweight | Vicente Luque | Lean | 58% |
Fight-by-Fight Breakdown
Joshua Van vs Tatsuro Taira
The Flyweight matchup features Joshua Van (8-1) taking on Tatsuro Taira (7-1). Taira is the bigger frame at 5'7" with a 5-inch reach advantage.
Van carries a modest Elo edge (1678 to 1620), the kind of gap that reflects a slightly better run of form rather than a talent chasm. Van rides a 5-fight win streak into this one.
Stylistically this is Van's striker game against Taira's wrestler approach. Van brings a versatile approach, while Taira looks to close distance and put the fight on the mat. Historically these archetypes are dead-even when they collide.
The submission threat is elevated here at 44%, with the model also seeing 24% KO/TKO and 32% decision probability.
The Pick: Joshua Van over Tatsuro Taira. This is essentially a pick'em. The model nudges toward Van at 52%, but there's almost nothing separating these two.
Kevin Holland vs Randy Brown
The Welterweight matchup features Kevin Holland (15-11) taking on Randy Brown (14-6). Holland will look to use a 3-inch reach edge to control distance.
There's a real Elo separation here: Brown at 1381 versus Holland at 1257. That 124-point gap typically reflects a meaningful difference in recent quality of competition and results.
Both fighters land in our "All-Rounder" archetype — fighters comfortable everywhere, able to strike or grapple depending on what the opponent gives them. When mirror matchups like this happen, the edge usually goes to whoever can impose their preferred pace and range.
The submission threat is elevated here at 38%, with the model also seeing 32% KO/TKO and 30% decision probability.
The Pick: Randy Brown over Kevin Holland. The model gives Brown a slight nod at 60% — this could easily go either way.
Tatiana Suarez vs Loopy Godinez
The Women's Strawweight matchup features Tatiana Suarez (7-1) taking on Loopy Godinez (8-5). Suarez is the bigger frame at 5'5" with a 5-inch reach advantage.
Suarez is rated at 1531 — 271 points above Godinez's 1260. Gaps this large usually mean one fighter has been consistently beating better opponents.
Both fighters land in our "Wrestler" archetype — fighters who win by dictating where the fight takes place, grinding out control time and wearing opponents down. When mirror matchups like this happen, the edge usually goes to whoever can impose their preferred pace and range.
The submission threat is elevated here at 50%, with the model also seeing 18% KO/TKO and 32% decision probability.
The Pick: Tatiana Suarez over Loopy Godinez. The model gives Suarez a slight nod at 58% — this could easily go either way.
Curtis Blaydes vs Josh Hokit
The Heavyweight matchup features Curtis Blaydes (13-5) taking on Josh Hokit (1-0). Blaydes is the bigger frame at 6'4" with a 7-inch reach advantage.
Blaydes is rated at 1634 — 395 points above Hokit's 1240. Gaps this large usually mean one fighter has been consistently beating better opponents.
There's a real chance this one doesn't go the distance — our model sees a 55% probability of a KO/TKO finish, with 24% submission and 21% decision.
The Pick: Curtis Blaydes over Josh Hokit. The model gives Blaydes a slight nod at 64% — this could easily go either way.
Dominick Reyes vs Johnny Walker
The Light Heavyweight matchup features Dominick Reyes (9-4) taking on Johnny Walker (7-6). Walker is the bigger frame at 6'6" with a 5-inch reach advantage.
There's a real Elo separation here: Reyes at 1529 versus Walker at 1432. That 97-point gap typically reflects a meaningful difference in recent quality of competition and results. Reyes rides a 3-fight win streak into this one.
Both fighters land in our "Knockout Artist" archetype — precision strikers who sit back, pick their shots, and carry fight-ending power. When mirror matchups like this happen, the edge usually goes to whoever can impose their preferred pace and range.
There's a real chance this one doesn't go the distance — our model sees a 52% probability of a KO/TKO finish, with 30% submission and 19% decision.
The Pick: Johnny Walker over Dominick Reyes. This is essentially a pick'em. The model nudges toward Walker at 54%, but there's almost nothing separating these two.
Azamat Murzakanov vs Paulo Costa
The Light Heavyweight matchup features Azamat Murzakanov (5-0) taking on Paulo Costa (6-4). There's a 3-inch height gap favoring Costa.
Murzakanov carries a modest Elo edge (1573 to 1513), the kind of gap that reflects a slightly better run of form rather than a talent chasm. Murzakanov rides a 5-fight win streak into this one.
Both fighters land in our "Striker" archetype — fighters with a well-rounded skill set. When mirror matchups like this happen, the edge usually goes to whoever can impose their preferred pace and range.
There's a real chance this one doesn't go the distance — our model sees a 48% probability of a KO/TKO finish, with 24% submission and 28% decision.
The Pick: Azamat Murzakanov over Paulo Costa. This is essentially a pick'em. The model nudges toward Murzakanov at 53%, but there's almost nothing separating these two.
Cub Swanson vs Nate Landwehr
The Featherweight matchup features Cub Swanson (14-10) taking on Nate Landwehr (5-4).
Swanson is rated at 1255 — 276 points above Landwehr's 979. Gaps this large usually mean one fighter has been consistently beating better opponents.
Stylistically this is Swanson's striker game against Landwehr's all-rounder approach. Swanson brings a versatile approach, while Landwehr is comfortable adjusting on the fly, mixing strikes and grappling as openings appear. Historically these archetypes are dead-even when they collide.
The submission threat is elevated here at 31%, with the model also seeing 29% KO/TKO and 40% decision probability.
The Pick: Cub Swanson over Nate Landwehr. This is essentially a pick'em. The model nudges toward Swanson at 54%, but there's almost nothing separating these two.
Kyle Daukaus vs Vicente Luque
The Middleweight matchup features Kyle Daukaus (3-4) taking on Vicente Luque (16-7). There's a 3-inch height gap favoring Daukaus.
There's a real Elo separation here: Luque at 1250 versus Daukaus at 1170. That 80-point gap typically reflects a meaningful difference in recent quality of competition and results.
The style clash matters here: Daukaus is most dangerous on the ground, constantly threatening chokes and joint locks, while Luque is comfortable adjusting on the fly, mixing strikes and grappling as openings appear. In our database, submission artists own a 56% win rate against all-rounders, giving Daukaus the stylistic edge.
There's a real chance this one doesn't go the distance — our model sees a 35% probability of a KO/TKO finish, with 47% submission and 18% decision.
The Pick: Vicente Luque over Kyle Daukaus. The model gives Luque a slight nod at 58% — this could easily go either way.
Methodology
Predictions are generated by our ensemble model combining LightGBM (65%) and CatBoost (35%), trained on every UFC fight since 1994. The model uses 23 features including Elo ratings, rolling 5-fight statistical averages, style matchup history, physical attributes, and market odds when available.
On our held-out test set (402 fights from January-September 2023), the model achieves 63.4% accuracy with a log-loss of 0.626. High-confidence picks (>75% probability) hit at 82.7%. For full model transparency, visit our Model page.