UFC 95: Sanchez vs Stevenson: Predictions & Analysis

Saturday, February 21, 2009·London, England, United Kingdom
Published February 27, 2026
Predictions are for entertainment purposes only and do not constitute financial advice. Please gamble responsibly.

UFC 95: Sanchez vs Stevenson lands on Saturday, February 21, 2009 in London, England, United Kingdom with 10 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

MatchupPickConfidenceProb
Diego Sanchez vs Joe StevensonLightweightJoe StevensonToss-up53%
Dan Hardy vs Rory MarkhamWelterweightDan HardyConfident75%
Nate Marquardt vs Wilson GouveiaMiddleweightNate MarquardtConfident69%
Demian Maia vs Chael SonnenMiddleweightDemian MaiaToss-up53%
Paulo Thiago vs Josh KoscheckWelterweightJosh KoscheckLean59%
Terry Etim vs Brian CobbLightweightTerry EtimStrong78%
Junior Dos Santos vs Stefan StruveHeavyweightJunior Dos SantosLean61%
Evan Dunham vs Per EklundLightweightPer EklundLean64%
Mike Ciesnolevicz vs Neil GroveHeavyweightMike CiesnoleviczLean62%
Paul Kelly vs Troy MandalonizWelterweightPaul KellyToss-up53%

Fight-by-Fight Breakdown

53%
Joe Stevenson
Sanchez
19-12
Elo 1139
Striker
VS
Stevenson
8-7
Elo 907
Wrestler

The Lightweight matchup features Diego Sanchez (19-12) taking on Joe Stevenson (8-7). Sanchez is the bigger frame at 5'10" with a 2-inch reach advantage.

Sanchez is rated at 1139 — 233 points above Stevenson's 907. Gaps this large usually mean one fighter has been consistently beating better opponents.

Stylistically this is Sanchez's knockout artist game against Stevenson's wrestler approach. Sanchez is patient on the feet, timing counters and loading up when he sees openings, while Stevenson looks to close distance and put the fight on the mat. Historically these archetypes are dead-even when they collide.

A few statistical edges stand out. Stevenson throws significantly more leather — a 0.1 sig. strike per minute gap. Stevenson is far more active with takedowns, averaging 1.6 more per 15 minutes. Sanchez has tighter striking defense, making opponents miss more often.

The Pick: Joe Stevenson over Diego Sanchez. This is essentially a pick'em. The model nudges toward Stevenson at 53%, but there's almost nothing separating these two.

Dan Hardy vs Rory Markham

Welterweight
75%
Dan Hardy
Hardy
5-4
Elo 1262
Wrestler
VS
Markham
1-1
Elo 943

The Welterweight matchup features Dan Hardy (5-4) taking on Rory Markham (1-1). Hardy will look to use a 3-inch reach edge to control distance.

Hardy is rated at 1262 — 319 points above Markham's 943. Gaps this large usually mean one fighter has been consistently beating better opponents.

A few statistical edges stand out. Hardy throws significantly more leather — a 0.1 sig. strike per minute gap. Markham is far more active with takedowns, averaging 0.0 more per 15 minutes. Hardy has tighter striking defense, making opponents miss more often.

The Pick: Dan Hardy over Rory Markham. We're leaning Hardy here at 75%, a solid but not overwhelming edge.

69%
Nate Marquardt
Marquardt
13-11
Elo 1064
All-Rounder
VS
Gouveia
6-3
Elo 1030
Submission Artist

The Middleweight matchup features Nate Marquardt (13-11) taking on Wilson Gouveia (6-3).

Marquardt carries a modest Elo edge (1064 to 1030), the kind of gap that reflects a slightly better run of form rather than a talent chasm.

Both fighters land in our "Submission Artist" archetype — ground specialists who hunt for finishes off their back or from top position. When mirror matchups like this happen, the edge usually goes to whoever can impose their preferred pace and range.

A few statistical edges stand out. Marquardt throws significantly more leather — a 0.0 sig. strike per minute gap. Marquardt is far more active with takedowns, averaging 2.9 more per 15 minutes. Marquardt has tighter striking defense, making opponents miss more often.

The Pick: Nate Marquardt over Wilson Gouveia. We're leaning Marquardt here at 69%, a solid but not overwhelming edge.

Demian Maia vs Chael Sonnen

Middleweight
53%
Demian Maia
Maia
22-10
Elo 1371
Wrestler
VS
Sonnen
7-6
Elo 1430
Wrestler

The Middleweight matchup features Demian Maia (22-10) taking on Chael Sonnen (7-6).

Sonnen carries a modest Elo edge (1430 to 1371), the kind of gap that reflects a slightly better run of form rather than a talent chasm.

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.

A few statistical edges stand out. Maia throws significantly more leather — a 0.4 sig. strike per minute gap. Sonnen is far more active with takedowns, averaging 1.8 more per 15 minutes. Sonnen has tighter striking defense, making opponents miss more often.

The Pick: Demian Maia over Chael Sonnen. This is essentially a pick'em. The model nudges toward Maia at 53%, but there's almost nothing separating these two.

59%
Josh Koscheck
Thiago
5-7
Elo 811
All-Rounder
VS
Koscheck
15-9
Elo 939
All-Rounder

The Welterweight matchup features Paulo Thiago (5-7) taking on Josh Koscheck (15-9).

There's a real Elo separation here: Koscheck at 939 versus Thiago at 811. That 128-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.

A few statistical edges stand out. Koscheck throws significantly more leather — a 2.1 sig. strike per minute gap. Koscheck is far more active with takedowns, averaging 1.1 more per 15 minutes. Thiago has tighter striking defense, making opponents miss more often.

The Pick: Josh Koscheck over Paulo Thiago. The model gives Koscheck a slight nod at 59% — this could easily go either way.

Terry Etim vs Brian Cobb

Lightweight
78%
Terry Etim
Etim
6-4
Elo 947
Wrestler
VS
Cobb
0-0
Elo 899

The Lightweight matchup features Terry Etim (6-4) taking on Brian Cobb (0-0).

Etim carries a modest Elo edge (947 to 899), the kind of gap that reflects a slightly better run of form rather than a talent chasm.

A few statistical edges stand out. Etim throws significantly more leather — a 2.3 sig. strike per minute gap. Cobb is far more active with takedowns, averaging 0.0 more per 15 minutes. Cobb has tighter striking defense, making opponents miss more often.

The Pick: Terry Etim over Brian Cobb. The model is firm on this one: Etim at 78%.

61%
Junior Dos Santos
Santos
15-7
Elo 1191
Striker
VS
Struve
13-10
Elo 878
All-Rounder

The Heavyweight matchup features Junior Dos Santos (15-7) taking on Stefan Struve (13-10). Struve is the bigger frame at 6'11" with a 7-inch reach advantage.

Santos is rated at 1191 — 313 points above Struve's 878. Gaps this large usually mean one fighter has been consistently beating better opponents.

Stylistically this is Santos's striker game against Struve's all-rounder approach. Santos brings a versatile approach, while Struve is comfortable adjusting on the fly, mixing strikes and grappling as openings appear. Historically these archetypes are dead-even when they collide.

A few statistical edges stand out. Santos throws significantly more leather — a 5.2 sig. strike per minute gap. Struve is far more active with takedowns, averaging 0.0 more per 15 minutes. Struve has tighter striking defense, making opponents miss more often.

The Pick: Junior Dos Santos over Stefan Struve. The model gives Santos a slight nod at 61% — this could easily go either way.

Evan Dunham vs Per Eklund

Lightweight
64%
Per Eklund
Dunham
11-8-1
Elo 1019
All-Rounder
VS
Eklund
1-1
Elo 874

The Lightweight matchup features Evan Dunham (11-8-1) taking on Per Eklund (1-1).

There's a real Elo separation here: Dunham at 1019 versus Eklund at 874. That 145-point gap typically reflects a meaningful difference in recent quality of competition and results.

A few statistical edges stand out. Eklund throws significantly more leather — a 1.9 sig. strike per minute gap. Eklund is far more active with takedowns, averaging 1.7 more per 15 minutes. Dunham has tighter striking defense, making opponents miss more often.

The Pick: Per Eklund over Evan Dunham. The model gives Eklund a slight nod at 64% — this could easily go either way.

62%
Mike Ciesnolevicz
Ciesnolevicz
1-0
Elo 972
VS
Grove
0-0
Elo 890

The Heavyweight matchup features Mike Ciesnolevicz (1-0) taking on Neil Grove (0-0).

There's a real Elo separation here: Ciesnolevicz at 972 versus Grove at 890. That 82-point gap typically reflects a meaningful difference in recent quality of competition and results.

A few statistical edges stand out. Grove throws significantly more leather — a 0.0 sig. strike per minute gap. Grove is far more active with takedowns, averaging 0.0 more per 15 minutes. Grove has tighter striking defense, making opponents miss more often.

The Pick: Mike Ciesnolevicz over Neil Grove. The model gives Ciesnolevicz a slight nod at 62% — this could easily go either way.

53%
Paul Kelly
Kelly
5-3
Elo 998
Wrestler
VS
Mandaloniz
1-0
Elo 1025

The Welterweight matchup features Paul Kelly (5-3) taking on Troy Mandaloniz (1-0).

The Elo gap here is razor-thin — Kelly at 998, Mandaloniz at 1025. On paper, this is as close to a coin flip as it gets.

A few statistical edges stand out. Mandaloniz throws significantly more leather — a 3.6 sig. strike per minute gap. Kelly is far more active with takedowns, averaging 2.7 more per 15 minutes. Mandaloniz has tighter striking defense, making opponents miss more often.

The Pick: Paul Kelly over Troy Mandaloniz. This is essentially a pick'em. The model nudges toward Kelly at 53%, but there's almost nothing separating these two.

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.