UFC 67: All or Nothing: Predictions & Analysis
UFC 67: All or Nothing lands on Saturday, February 3, 2007 in Las Vegas, Nevada, USA with 9 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 |
|---|---|---|---|
| Anderson Silva vs Travis LutterMiddleweight | Anderson Silva | Strong | 79% |
| Mirko Filipovic vs Eddie SanchezHeavyweight | Eddie Sanchez | Lean | 59% |
| Roger Huerta vs John HalversonLightweight | Roger Huerta | Strong | 88% |
| Quinton Jackson vs Marvin EastmanLight Heavyweight | Quinton Jackson | Lean | 65% |
| Patrick Cote vs Scott SmithMiddleweight | Scott Smith | Toss-up | 51% |
| Terry Martin vs Jorge RiveraMiddleweight | Terry Martin | Lean | 57% |
| Frankie Edgar vs Tyson GriffinLightweight | Frankie Edgar | Toss-up | 52% |
| Lyoto Machida vs Sam HogerLight Heavyweight | Sam Hoger | Confident | 65% |
| Dustin Hazelett vs Diego SaraivaLightweight | Dustin Hazelett | Toss-up | 52% |
Fight-by-Fight Breakdown
Anderson Silva vs Travis Lutter
The Middleweight matchup features Anderson Silva (17-6) taking on Travis Lutter (2-3). Silva is the bigger frame at 6'2" with a 2-inch reach advantage.
Silva is rated at 1154 — 188 points above Lutter's 966. Gaps this large usually mean one fighter has been consistently beating better opponents.
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. Silva throws significantly more leather — a 12.3 sig. strike per minute gap. Lutter is far more active with takedowns, averaging 1.0 more per 15 minutes. Silva has tighter striking defense, making opponents miss more often.
The Pick: Anderson Silva over Travis Lutter. The model is firm on this one: Silva at 79%.
Mirko Filipovic vs Eddie Sanchez
The Heavyweight matchup features Mirko Filipovic (4-6) taking on Eddie Sanchez (3-2).
Filipovic is rated at 1145 — 226 points above Sanchez's 919. Gaps this large usually mean one fighter has been consistently beating better opponents.
The style clash matters here: Filipovic is patient on the feet, timing counters and loading up when he sees openings, while Sanchez brings a versatile approach. In our database, knockout artists own a 54% win rate against strikers, giving Filipovic the stylistic edge.
A few statistical edges stand out. Sanchez throws significantly more leather — a 1.9 sig. strike per minute gap. Sanchez is far more active with takedowns, averaging 0.0 more per 15 minutes. Filipovic has tighter striking defense, making opponents miss more often.
The Pick: Eddie Sanchez over Mirko Filipovic. The model gives Sanchez a slight nod at 59% — this could easily go either way.
Roger Huerta vs John Halverson
The Lightweight matchup features Roger Huerta (6-1) taking on John Halverson (0-1).
Huerta is rated at 1257 — 426 points above Halverson's 831. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Huerta throws significantly more leather — a 4.7 sig. strike per minute gap. Huerta is far more active with takedowns, averaging 6.0 more per 15 minutes. Halverson has tighter striking defense, making opponents miss more often.
The Pick: Roger Huerta over John Halverson. The model is firm on this one: Huerta at 88%.
Quinton Jackson vs Marvin Eastman
The Light Heavyweight matchup features Quinton Jackson (7-5) taking on Marvin Eastman (1-3). There's a 4-inch height gap favoring Jackson.
Jackson is rated at 1296 — 487 points above Eastman's 809. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Eastman throws significantly more leather — a 1.6 sig. strike per minute gap. Eastman is far more active with takedowns, averaging 0.0 more per 15 minutes. Jackson has tighter striking defense, making opponents miss more often.
The Pick: Quinton Jackson over Marvin Eastman. The model gives Jackson a slight nod at 65% — this could easily go either way.
Patrick Cote vs Scott Smith
The Middleweight matchup features Patrick Cote (10-10) taking on Scott Smith (1-2). Cote will look to use a 5-inch reach edge to control distance.
Cote is rated at 1221 — 385 points above Smith's 836. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Smith throws significantly more leather — a 0.9 sig. strike per minute gap. Cote is far more active with takedowns, averaging 0.3 more per 15 minutes. Smith has tighter striking defense, making opponents miss more often.
The Pick: Scott Smith over Patrick Cote. This is essentially a pick'em. The model nudges toward Smith at 51%, but there's almost nothing separating these two.
Terry Martin vs Jorge Rivera
The Middleweight matchup features Terry Martin (2-3) taking on Jorge Rivera (7-7). Rivera is the bigger frame at 6'1" with a 2-inch reach advantage.
Rivera is rated at 1174 — 326 points above Martin's 848. Gaps this large usually mean one fighter has been consistently beating better opponents.
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.
A few statistical edges stand out. Rivera throws significantly more leather — a 0.8 sig. strike per minute gap. Martin is far more active with takedowns, averaging 3.1 more per 15 minutes. Rivera has tighter striking defense, making opponents miss more often.
The Pick: Terry Martin over Jorge Rivera. The model gives Martin a slight nod at 57% — this could easily go either way.
Frankie Edgar vs Tyson Griffin
The Lightweight matchup features Frankie Edgar (18-10-1) taking on Tyson Griffin (8-5).
Edgar is rated at 1185 — 260 points above Griffin's 925. Gaps this large usually mean one fighter has been consistently beating better opponents.
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. Griffin throws significantly more leather — a 0.0 sig. strike per minute gap. Griffin is far more active with takedowns, averaging 8.2 more per 15 minutes. Edgar has tighter striking defense, making opponents miss more often.
The Pick: Frankie Edgar over Tyson Griffin. This is essentially a pick'em. The model nudges toward Edgar at 52%, but there's almost nothing separating these two.
Lyoto Machida vs Sam Hoger
The Light Heavyweight matchup features Lyoto Machida (15-8) taking on Sam Hoger (2-2).
Machida is rated at 1493 — 568 points above Hoger's 925. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Hoger throws significantly more leather — a 1.2 sig. strike per minute gap. Hoger is far more active with takedowns, averaging 1.1 more per 15 minutes. Machida has tighter striking defense, making opponents miss more often.
The Pick: Sam Hoger over Lyoto Machida. We're leaning Hoger here at 65%, a solid but not overwhelming edge.
Dustin Hazelett vs Diego Saraiva
The Lightweight matchup features Dustin Hazelett (5-4) taking on Diego Saraiva (0-2).
Hazelett is rated at 973 — 199 points above Saraiva's 774. Gaps this large usually mean one fighter has been consistently beating better opponents.
A few statistical edges stand out. Hazelett throws significantly more leather — a 0.3 sig. strike per minute gap. Saraiva is far more active with takedowns, averaging 0.0 more per 15 minutes. Saraiva has tighter striking defense, making opponents miss more often.
The Pick: Dustin Hazelett over Diego Saraiva. This is essentially a pick'em. The model nudges toward Hazelett at 52%, 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.