Gridiron · Game Center · 2026
The Fourth Down Room
Go, kick or punt — and what the win probability said.
Went for it on 25.9% of 27 fourth downs where the rest of the league goes 14.4%.
How the baseline is built · no recommendation engine ▸
There is no recommendation engine here. Scoring the choice a coach did NOT make would mean inventing a win-probability figure for a play that never happened, so the baseline is the league’s own revealed behaviour instead — what all 32 teams actually did from the same spot, 2018–2026.
895 real fourth-down decisions in the first 5 weeks of the 2026 regular season. 85 more snaps are set aside — penalties that wiped the play before it resolved, and victory-formation kneels — because neither one decided anything.
Every fourth down. Every regular-season fourth down that resolved into a real decision. 30 of 32 teams clear 20 decisions in every state on the field; a grid cell under 25 decisions is withheld rather than painted.
There is no recommendation engine here. Scoring the choice a coach did NOT make would mean inventing a win-probability figure for a play that never happened, so the baseline is the league’s own revealed behaviour instead — what all 32 teams actually did from the same spot, 2018–2026.
Painted after the last game's play-by-play landed · the room repaints as each game's play-by-play lands, usually within two hours of the final, or the next morning when its release runs late
Reading today’s slate…
The signature object · and the filter
The decision grid
Pooled 2018–2026, so every cell is thousands of decisions rather than a season of noise. Read the middle of the top row before trusting anything else: the league goes for it LESS at the opponent's 16-25 than at the 26-38, because 16-25 is a comfortable field goal and 26-38 is a long one. A grid that fell smoothly with field position would be a grid that had lost the plot.
League 2018–2026
| To gain | |||||||
|---|---|---|---|---|---|---|---|
n/aFourth and 7-10 from the Goal line is not a possible state. | |||||||
n/aFourth and 11+ from the Goal line is not a possible state. |
Numeral = go-rate · small figure = decisions in the cell · n/a = a state the field cannot produce
League 2018–2026 · every state on the field
The call sheet
The bar is what coaches did. The rule across it is what this room's own win-probability means say they should have done: on every cell where all three choices cleared 25 plays, the model prefers going when going returned at least as much win probability as the better of kicking and punting, weighted by the decisions actually made there. Neither number is a forecast of a road not taken — both are measured on the plays themselves.
On fourth and 4-6 the league went for it 14.5% of the time while its own returns favoured going on 100.0% of the same 886 snaps — the widest gap on the sheet.
Thin sample: 5 qualified · too few rows to read as a set
Go over expected · every state on the field
The aggression ladder
Raw go-rate lies about who is aggressive, because it does not know which spots a team stood in. Go over expected does: it subtracts the league's own pooled rate in the SAME cells, weighted by how often this team was there. The two orderings are not the same list, and where a team moves between them is the finding.
Decisions made
- 1
DetroitLions+11.526% of 27Detroit Lions, go over expected 11.5 points, 26 percent of 27 decisions - 2
New OrleansSaints+9.332% of 28New Orleans Saints, go over expected 9.3 points, 32 percent of 28 decisions - 3
CarolinaPanthers+8.927% of 30Carolina Panthers, go over expected 8.9 points, 27 percent of 30 decisions - 4
PhiladelphiaEagles+7.923% of 30Philadelphia Eagles, go over expected 7.9 points, 23 percent of 30 decisions - 5
MiamiDolphins+7.821% of 28Miami Dolphins, go over expected 7.8 points, 21 percent of 28 decisions - 6
Los AngelesChargers+7.321% of 28Los Angeles Chargers, go over expected 7.3 points, 21 percent of 28 decisions - 7
Los AngelesRams+6.724% of 25Los Angeles Rams, go over expected 6.7 points, 24 percent of 25 decisions - 8
Green BayPackers+5.028% of 32Green Bay Packers, go over expected 5.0 points, 28 percent of 32 decisions - 9
ChicagoBears+3.938% of 26Chicago Bears, go over expected 3.9 points, 38 percent of 26 decisions - 10
New EnglandPatriots+3.822% of 27New England Patriots, go over expected 3.8 points, 22 percent of 27 decisions - 11
Tampa BayBuccaneers+1.618% of 38Tampa Bay Buccaneers, go over expected 1.6 points, 18 percent of 38 decisions - 12
ClevelandBrowns+1.620% of 30Cleveland Browns, go over expected 1.6 points, 20 percent of 30 decisions - 13
DallasCowboys+0.315% of 26Dallas Cowboys, go over expected 0.3 points, 15 percent of 26 decisions - 14
Kansas CityChiefs+0.126% of 27Kansas City Chiefs, go over expected 0.1 points, 26 percent of 27 decisions - 15
WashingtonCommanders−0.920% of 35Washington Commanders, go over expected -0.9 points, 20 percent of 35 decisions - 16
TennesseeTitans−1.413% of 30Tennessee Titans, go over expected -1.4 points, 13 percent of 30 decisions - 17
CincinnatiBengals−1.615% of 26Cincinnati Bengals, go over expected -1.6 points, 15 percent of 26 decisions - 18
HoustonTexans−1.821% of 33Houston Texans, go over expected -1.8 points, 21 percent of 33 decisions - 19
Las VegasRaiders−2.021% of 29Las Vegas Raiders, go over expected -2.0 points, 21 percent of 29 decisions - 20
PittsburghSteelers−3.210% of 30Pittsburgh Steelers, go over expected -3.2 points, 10 percent of 30 decisions - 21
BaltimoreRavens−4.817% of 24Baltimore Ravens, go over expected -4.8 points, 17 percent of 24 decisions - 22
SeattleSeahawks−4.818% of 28Seattle Seahawks, go over expected -4.8 points, 18 percent of 28 decisions - 23
New YorkGiants−5.48% of 26New York Giants, go over expected -5.4 points, 8 percent of 26 decisions - 24
New YorkJets−5.713% of 30New York Jets, go over expected -5.7 points, 13 percent of 30 decisions - 25
ArizonaCardinals−6.213% of 30Arizona Cardinals, go over expected -6.2 points, 13 percent of 30 decisions - 26
DenverBroncos−6.37% of 28Denver Broncos, go over expected -6.3 points, 7 percent of 28 decisions - 27
MinnesotaVikings−7.78% of 36Minnesota Vikings, go over expected -7.7 points, 8 percent of 36 decisions - 28
AtlantaFalcons−8.98% of 24Atlanta Falcons, go over expected -8.9 points, 8 percent of 24 decisions - 29
IndianapolisColts−9.321% of 29Indianapolis Colts, go over expected -9.3 points, 21 percent of 29 decisions - 30
JacksonvilleJaguars−15.60% of 20Jacksonville Jaguars, go over expected -15.6 points, 0 percent of 20 decisions
2 more teams — Bills, 49ers — had fewer than 20 decisions in every state on the field and are counted but not ranked.
Bar diverges from the league rate · under 20 decisions the figure is withheld, not guessed
2026 · every state on the field
What each choice actually returned
Mean win probability added, measured on the plays themselves — not a forecast of the road not taken. Every figure below is withheld under 25 plays, because the rare choice in a cell is rare precisely because it is unusual, and its mean is the loudest number in the row for exactly that reason.
Went for it
16719% of choices
Mean WP added+0.018
Measured on 94 of them — the rest sit in cells too thin to average.
Converted59.6%
Drive ended in points47.9%
Kicked
23426% of choices
Mean WP added+0.016
Measured on 194 of them — the rest sit in cells too thin to average.
Made86.1%
Punted
49455% of choices
Mean WP added+0.009
Measured on 488 of them — the rest sit in cells too thin to average.