Week 10 2026 · November 7, 2026
Air Force at Army, Week 10 2026: who deserved to win?
Air Force beat Army 24–21, and the replays back it up: with the way both teams actually played, Air Force wins 9 of 10. Army had the bounces: 3rd & 4th downs alone were worth 20 points of win probability to Army.
An off day for Army: it played far below what the matchup promised. In a fresh game against Air Force it would win 56% of the time; with this day’s form, 8%. The numbers
Before kickoff Army was a 59% favorite. The biggest swing (Q4, 7:11 left): Air Force was stopped on 4th & 2, worth 12 points of win probability to Army.
Final
| 24 | |
| 21 |
Replay with same day's form
Luck index +8 Air Force about even · −8 Army
Each team’s own plays from this game, resampled into new drives 4,000 times: with the way both teams actually played, how often does this performance win? How the replay works
Ten replays. Air Force wins 9, Army wins 1.
- 1 AF 45 ARMY 10
- 2 AF 28 ARMY 0
- 3 AF 31 ARMY 7
- 4 AF 24 ARMY 3
- 5 AF 24 ARMY 7
- 6 AF 20 ARMY 6
- 7 AF 31 ARMY 20
- 8 AF 21 ARMY 14
- 9 AF 17 ARMY 14
- 10 AF 0 ARMY 7
Our prediction before kickoff
We had Army by 7.5, 68% to win. Air Force won by 3, a result we gave 32%. The final margin was 10.5 points from ours; 48% of games like this end further from the forecast than that.
Show as a table
| Outcome | Chance |
|---|---|
| Air Force win | 31.8% |
| Army win | 68.2% |
| Middle 50%: Air Force by 3 to Army by 18 | 50% |
| Middle 90%: Air Force by 19 to Army by 34 | 90% |
| Middle 95%: Air Force by 24 to Army by 39 | 95% |
| Exactly Army by 3 | 6.7% |
| Exactly Air Force by 3 | 5.6% |
| Exactly Army by 7 | 5.6% |
| Exactly Army by 14 | 4.1% |
| Exactly Air Force by 7 | 3.7% |
Most of the distance between a forecast and a final score is luck: even with both teams’ strength known exactly, one game’s bounces, kicks and calls move the final margin by about ±13 points. Made Sat, Nov 7, 6:54 pm ET and frozen at kickoff. How our predictions have done
Three other ways to ask
Each answers a different question, so none of them replaces the replay above.
Before kickoff
The closing betting line, turned into a probability. What everyone knew before the game.
Same teams, fresh game
The line plus what this game showed, weighted by how much one game can tell. It stays close to the line because one game says little.
Only coin-flips re-rolled
Every kick, fumble bounce, conversion and judgment call redrawn; everything else fixed. The narrowest view of luck.
An off day for Army
It played far below what the matchup promised. In a fresh game against Air Force it would win 56% of the time; with this day’s form, 8%.
Same teams, fresh game
Replay with same day's form
48 points apart for Army: the gap is how differently this game went from what the two teams usually are.
| Unit | This game | Usual level | Better or worse than usual |
|---|---|---|---|
| Air Force offenseEPA per play gained | +0.06 | +0.16 | worse by 0.10 |
| Air Force defenseEPA per play allowed | +0.14 | +0.21 | better by 0.07 |
| Army offenseEPA per play gained | +0.14 | +0.12 | better by 0.02 |
| Army defenseEPA per play allowed | +0.06 | +0.19 | better by 0.13 |
EPA (expected points added) per play on competitive snaps, turnovers left out because they are valued as luck. Usual level: the team’s earlier games this season plus half of last season, pulled toward the league average. One team’s defense and the other team’s offense are the same snaps, so one game can’t fully say whose day it was; it shows how far this one was from both teams’ norms.
How 4,000 replays ended
Air Force wins 92% of them, Army 8%, counting the 1% still level after regulation as half each. The line is what actually happened: Air Force by 3.
Show as a table
| Final margin in the replays | Share of replays |
|---|---|
| Air Force by 17+ | 47.8% |
| Air Force by 9–16 | 22.9% |
| Air Force by 1–8 | 20.8% |
| Level after regulation | 0.7% |
| Army by 1–8 | 5.6% |
| Army by 9–16 | 2.0% |
| Army by 17+ | 0.2% |
Where the luck was
What the luck was worth
Every lucky and unlucky play, weighted by the moment it happened: its swing in win probability, added up by kind. A missed kick in a decided game counts for nothing; the same kick at the end of a tie game can be most of a win.
The kicks
How likely each kicker was to make that kick (his own record, the distance), and what happened.
- D. Jones, 46 yds missed · 62% expected
- C. Cremascoli, 21 yds made · 95% expected
Penalties: Air Force 1 for 5 yards, Army 1 for 10 yards
Every accepted flag, in order, and what it did to the helped team’s chance of winning at that moment, including any play it wiped out (points on the scoreboard in grey). A flag in a decided game is worth nothing; one at the turn of a close game can be worth most of a win. Judgment calls count toward luck, pre-snap fouls mostly don’t. How calls are valued
| When | Flag | Win probability for |
|---|---|---|
| Q2 0:48 | Holding on Army, 10 yards | +3% AF +1.0 pts |
| Q4 8:51 | False Start on Air Force, 5 yards · pre-snap | +2% ARMY +0.7 pts |
When it happened
Army’s chance of winning
As low as 0% and as high as 71%. Numbers mark the biggest luck moments, listed below.
| # | When | What happened | Win probability for | Next drive |
|---|---|---|---|---|
| 1 | Q1 6:30 | D. Jones missed a 46-yard field goalKicks · 62% expected for him, 5 of 8 from 45+ before | +5% AF | ARMY: Turnover on downs |
| 2 | Q3 7:12 | Army converted 3rd & 53rd & 4th downs · 36% expected | +7% ARMY | ARMY: Touchdown |
| 3 | Q3 4:42 | Air Force was stopped on 3rd & 33rd & 4th downs · 62% expected | +7% ARMY | AF: Turnover on downs |
| 4 | Q3 4:06 | Air Force was stopped on 4th & 33rd & 4th downs · 61% expected | +10% ARMY | AF: Touchdown |
| 5 | Q4 12:55 | Army converted 3rd & 83rd & 4th downs · 33% expected | +9% ARMY | ARMY: Turnover |
| 6 | Q4 7:50 | Air Force was stopped on 3rd & 23rd & 4th downs · 63% expected | +5% ARMY | AF: Turnover on downs |
| 7 | Q4 7:11 | Air Force was stopped on 4th & 23rd & 4th downs · 62% expected | +12% ARMY | AF: End of game |
| 8 | Q4 5:48 | Army was stopped on 3rd & 83rd & 4th downs · 34% expected | +5% AF | ARMY: Punt |
Adjust the assumptions
Disagree with how much of a fumble bounce or a pass interference call is luck? Change it and the coin-flip replay reruns in your browser.
Only coin-flips re-rolled
Air Force 87% · Army 13%
- Final margin
- Air Force by 3
- Luck in points
- 2.9 for Army
- Luck-adjusted margin
- Air Force by 5.9
- Replay with same day's form
- Air Force 92% · Army 8% unchanged: why
About these numbers
Play-by-play and expected points from CollegeFootballData.com via cfbfastR; win probability from our own model of the score, the possession and the betting line; kicks valued against each kicker’s own record. College play-by-play has no charting of drops or interception-worthy throws and no injury reports, so those kinds of luck aren’t counted here.
Methodology and validation · All Week 10 2026 games ·
Air Force ·
Army
More from Week 10 2026
- Northern Illinois at San José State SJSU 30–19 · replay 28% for the winner
- South Florida at East Carolina ECU 20–17 · replay 44% for the winner
- Hawai'i at UTEP HAW 17–14 · replay 51% for the winner
- Rice at North Texas UNT 52–23 · replay 83% for the winner
- UTSA at Florida Atlantic FAU 60–29 · replay 94% for the winner
- Temple at Navy NAVY 42–35 · replay 96% for the winner
- Charlotte at UAB UAB 23–12 · replay 97% for the winner
- Wyoming at UNLV WYO 41–35 · replay 98% for the winner
- New Mexico at Nevada UNM 31–3 · replay 100% for the winner
- Tulsa at Tulane TLSA 60–10 · replay 100% for the winner
- BYU at Utah UTAH 28–20 · replay 26% for the winner
- Iowa State at Baylor BAY 42–31 · replay 31% for the winner