For the complete documentation index, see llms.txt. Markdown variants of the ranked boards (dynasty and fantasy rankings for NFL, NBA, MLB and CFB) are available by appending .md to those URLs or by sending Accept: text/markdown; other pages answer 404.
1 other measure was inside a third of the league's own spread — two clubs doing the same thing, so it is not shown.
Drawn from the weekly play-by-play file, which paints on the Monday 4:00 AM ET sync after the game.
The model against the market, the momentum underneath, every drive — scrub to replay it
How the game was won
The model and the market were 2.6 win-probability points apart on the average play, and 8 apart at the widest — with the model the more convinced about Commanders.
MarketModelmodel higher on Commandershigher on Browns151 of 163 plays carry both curves
(10:12) (Shotgun) 4-D.Watson pass short left to 2-A.Cooper for 46 yards, TOUCHDOWN.
Swing −18.5 for CommandersExpected points −5.35 for CommandersThe model had Commanders 4 points higher than the market did.play 87
The solid line is the betting market's home win probability; the dashed line is the play-by-play model's. The shaded band between them is the disagreement — emerald where the model liked the home team more, red where it liked the away team more. Drag across the curve or use arrow keys to replay the game; gold diamonds mark the biggest swings.
Highest-leverage plays
3rd · 10:12WAS +18% win prob(10:12) (Shotgun) 4-D.Watson pass short left to 2-A.Cooper for 46 yards, TOUCHDOWN.
3rd · 3:55WAS +12% win prob(3:55) (Shotgun) 4-D.Watson pass deep left to 2-A.Cooper pushed ob at WAS 26 for 26 yards (22-D.Forrest).
2nd · 0:23WAS +11% win prob(:23) 11-C.Wentz up the middle for 1 yard, TOUCHDOWN.
1st · 3:56CLE +10% win prob(3:56) 41-J.Williams left end to CLE 41 for -1 yards (90-J.Clowney, 95-M.Garrett).
2nd · 6:09WAS +10% win prob(6:09) (Shotgun) 11-C.Wentz pass deep right to 1-J.Dotson to CLE 49 for 20 yards (23-M.Emerson).
2nd · 2:59WAS +9% win prob(2:59) (Shotgun) 11-C.Wentz pass short left to 82-L.Thomas to CLE 17 for 15 yards (23-M.Emerson).
2nd · 6:54CLE +9% win prob
SettledThe modelled figures are the league play-by-play model's, not ours.
How the points landed
The margin ledger
Amari Cooper's 46-yard touchdown catch with 10:12 left in the 3rd put Cleveland Browns ahead for good. The lead never changed over the 3 scores that followed.
Lead
1st9:26Cade York·37-yd field goal37-yard field goalholder C.Bojorquez · snap C.Hughlett+33–0
Browns ahead 5–3 on categories, including the biggest gap of the duel — turnovers.
Expected points added, per play
The centre line is an average play. A bar to the right of it is a side that gained more than the situation was worth; a bar to the left is a side that lost ground. All six bars share one scale, ±0.35 points.
Every snapexpected points added per play, all downs
+0.18Browns: +0.18 expected points added per play
−0.18Commanders: −0.18 expected points added per play
Dropping backexpected points added per dropback
+0.27Browns: +0.27 expected points added per play
−0.26Commanders: −0.26 expected points added per play
Running itexpected points added per rush
+0.09Browns: +0.09 expected points added per play
−0.10Commanders: −0.10 expected points added per play
Neither side “wins” volume or play-calling mix, so neither is drawn as a duel: Browns ran 50 snaps at a 50% dropback rate against Commanders’s 68 at 47%. Red-zone trips: Browns 5, Commanders 1.
NoteBrowns won the down-to-down efficiency fight: 0.18 expected points added per play vs -0.18.
Derived from the play-by-play, no model
The Read
12 of 12 readings cleared their snap floor and were tested against four comparisons: this week's whole slate, the team's own season, the week before, and the team's own ordinary spread. Every bar below is set in that team's own week-to-week swing, never in league points — one team's swing runs 1.6 to 3.1 times the entire league's spread.
highest in the league that weekAgainst the weekFourth Down
WAS's fourth-and-short go rate, 100.0%, was the highest of the 20 team-games charted in week 17 — 33.3 points clear of the next team along.
Past their previous high of 66.7% in week 11.
2.3 times their own weekly swing above their number.
3 fourth-and-short calls this game, floor 3 — 13 of their games behind the ruler, and their own week-to-week swing is 28.1 points.
lowest in the league that weekAgainst the weekOver Expected
WAS's pass rate over expected, −20.5 pts, was the lowest of the 30 team-games charted in week 17 — 0.5 points clear of the next team along.
Past their previous low of −17.5 pts in week 16.
68 snaps this game, floor 20 — 17 of their games behind the ruler, and their own week-to-week swing is 8.4 points.
CLE's sack or hit rate turned over: 0.0% in week 16 against 15.6% here — they stayed blocked then and got home now, a turn of 2.3 of their own weekly swings across the two.
32 dropbacks this game, floor 12 — 17 of their games behind the ruler, and their own week-to-week swing is 6.7 points.
CLE's pass rate over expected turned over: −23.4 pts in week 16 against −3.8 pts here — they ran more than the situation asked then and threw more than the situation asked now, a turn of 2.8 of their own weekly swings across the two.
50 snaps this game, floor 20 — 17 of their games behind the ruler, and their own week-to-week swing is 7.0 points.
The season-grain rooms, pointed at this one game
Was this normal for them?
12 of 12 readings cleared their snap floor. Every deviation below is measured in that team's own game-to-game swing, not in league points — because one game's swing runs from 1.6 to 3.1 times the whole league's spread.
their week-to-week swingall 32 teams
upper band = their week-to-week swing · lower rule = all 32 teams · scale -29 pts to 14 pts
inside their normal wobble · +4.3 vs their 11.3%, and they swing ±6.7 week to week (+0.64× that swing) · 32 dropbacks
Commanders28.0%
inside their normal wobble · +9.2 vs their 18.8%, and they swing ±9.8 week to week (+0.94× that swing) · 25 dropbacks
NoteWAS's fourth-and-short go rate was the night's one real departure: 100.0%, 64.7 points above their season mean of 35.3% and 2.3 times their own 28.1-point weekly swing.
The Game Day Roster
Who was out, who dressed and never took a snap, and who was on the field how much. Game-day list and snap counts from the weekly roster and snap feeds. Practice-squad and injured-reserve players are not shown — they were never on the game-day list.
Cleveland Browns
48 dressed · 7 inactive
75Joel BitonioG · Every snap100%57 snaps
77Wyatt TellerG · Every snap100%57 snaps
55Ethan PocicC · Every snap100%57 snaps
71Jedrick WillsT · Every snap100%57 snaps
4Deshaun WatsonQB · Full-time98%56 snaps
85David NjokuTE · Full-time93%53 snaps
11Donovan Peoples-JonesWR · Full-time86%49 snaps
78Jack ConklinT · Heavy rotation65%37 snaps
2Amari CooperWR · Heavy rotation61%35 snaps
24Nick ChubbRB · Heavy rotation56%32 snaps
88Harrison BryantTE · Heavy rotation53%30 snaps
84Pharaoh BrownTE · Rotational40%23 snaps
12Mike WoodsWR · Rotational37%21 snaps
66James HudsonT · Rotational35%20 snaps
27Kareem HuntRB · Rotational32%18 snaps
18David BellWR · Rotational26%15 snaps
34Jerome FordRB · Situational12%7 snaps
16Jaelon DardenWR · Situational4%2 snaps
7Jacoby BrissettQB · Situational2%1 snap
Inactive · 7
Thomas GrahamCBIsaiah ThomasDETommy TogiaiDTBen StilleDTKellen MondQBDemetric FeltonRBChristopher HubbardT
Washington Commanders
48 dressed · 7 inactive · 2 never used
68Andrew NorwellG · Every snap100%69 snaps
72Charles LenoT · Every snap100%69 snaps
11Carson WentzQB · Every snap100%69 snaps
71Wes SchweitzerG · Every snap100%69 snaps
82Logan ThomasTE · Full-time83%57 snaps
17Terry McLaurinWR · Full-time81%56 snaps
1Jahan DotsonWR · Heavy rotation77%53 snaps
53Trai TurnerG · Heavy rotation70%48 snaps
76Samuel CosmiT · Heavy rotation70%48 snaps
10Curtis SamuelWR · Heavy rotation64%44 snaps
78Cornelius LucasT · Heavy rotation61%42 snaps
8Brian RobinsonRB · Heavy rotation52%36 snaps
41Jonathan WilliamsRB · Rotational46%32 snaps
87John BatesTE · Rotational43%30 snaps
85Cole TurnerTE · Situational20%14 snaps
89Cam SimsWR · Situational17%12 snaps
2Dyami BrownWR · Situational16%11 snaps
Inactive · 7
Benjamin St-JusteCBJames Smith-WilliamsDEChris PaulGSam HowellQBAntonio GibsonRBKamren CurlSSSaahdiq CharlesT
7 players played under 8 snaps, so their shares read as a dash rather than a number. 6 lines have no expected-points read and sit off the plane.
Expected points are modelled in full PPR, so the “vs expected” column stays in that unit whichever format the pills are set to. Switching the pills changes the points column, not the plane.
The field map
Every snap, where it happened
The whole game as one hundred yards. The Commanders attack right, the Browns attack left, so a change of possession is a reversal you can see. Reading down is the order the snaps were played — not the clock, so a two-minute drill gets the same room as any other fourteen snaps. This game is final.
Browns←Commanders→
Q1Q2Q3Q4
D.Watson pass+20% win probabilitymoment 4 of 4
(10:12) (Shotgun) 4-D.Watson pass short left to 2-A.Cooper for 46 yards, TOUCHDOWN.
Q3 10:12 · Browns · 3rd & 5 at WAS 46 · gained 46 · +5.35 EP · +20.4% win probability
149 snaps placed · 14 without a recorded yard line, left off the map · 4 marked moments — the largest win-probability swings, one per drive.
The Film Room · post-game
Post-game film: 163 plays across 20 drives, personnel groupings on 163 snaps, manual charting on 137. Everything here paints once the weekly sync ingests the game — there is no live play-level feed in this product, so nothing on this page updates while a game is being played.
Possession by possession
The field rail
6 of 20 drives ended in points. The longest march was WAS moving 96 yards from the WAS 4 for a touchdown. Each bar is the ground a drive actually covered; WAS attacks right, CLE attacks left. Hatching marks a trip inside the twenty.
Every snap
Play stream
163 of 163 plays
Team
Quarter
Down
Play type
Expected points added
Event
Charted
Plays shown
163
EPA per play
-0.02
Success rate
36%
Yards
561
Who was on the field
Personnel groupings
Offensive grouping on every pass and run. A group needs five snaps in this game before it gets a number — under that the sample is a coin flip and the cell reads a dash instead. The names of the eleven on the field are only recorded from 2023 onward, so this game gives the grouping without the roster.
Commanders1 RB, 1 TE, 3 WR41-0.3363%
Browns1 RB, 1 TE, 3 WR21+0.2562%
Commanders1 RB, 2 TE, 2 WR20-0.0320%
Browns1 RB, 2 TE, 2 WR15-0.1447%
Browns1 RB, 3 TE, 1 WR14+0.4121%
Commanders1 RB, 3 TE, 1 WR6+0.170%
Commanders0 RB, 1 TE, 4 WR1——
snapsepapass rate
163 plays · ranked by the win probability each one moved
Every play
Ball
When
Play
Only
Who
163 plays
Bar length is win probability the play moved
1st quarter38 plays
Punt10 plays, from the Browns 25 to midfield
How the play was built
Empty backfield, nobody in motion.
Thrown on the first read, it should have been intercepted.
FormationEmpty backfieldOffense on the fieldOne back, one tight end and three receiversDefense on the fieldFour linemen, one linebacker and six backsRoute runOutCoverageCover 1, man with a free safetyMan or zoneManIn the boxSix defendersRushing the passerFourPressure (charted)The passer was kept cleanTime to throw3.1 seconds
Intercepted3 plays, from the Commanders 20 to the Commanders 24
Browns3Commanders0
Field goal5 plays, from the Commanders 36 to the Commanders 19
How the play was built
Two in the backfield, a man in motion.
FormationSingle backOffense on the fieldOne back, one tight end and three receiversDefense on the fieldFour linemen, two linebackers and five backsIn the boxSeven defenders
Turnover on downs10 plays, from the Commanders 22 to the Browns 40
How the play was built
Nobody in motion.
FormationShotgunOffense on the fieldOne back, one tight end and three receiversDefense on the fieldFour linemen, two linebackers and five backsIn the boxSeven defenders
Turnover on downs7 plays, from the Browns 42 to the Commanders 3
The period ended2 plays
2nd quarter38 plays
Intercepted5 plays, from the Commanders 3 to the Commanders 12
Punt4 plays, from the Browns 47 to the Browns 49
How the play was built
Two in the backfield, a quarterback sneak, a man in motion.
FormationSingle backOffense on the fieldOne back, two tight ends and two receiversDefense on the fieldSix linemen, two linebackers and three backsIn the boxNine defenders
Browns3Commanders6
Browns3Commanders7
Touchdown26 plays, from the Commanders 4 to the Browns 1
The period ended3 plays
3rd quarter37 plays
Punt5 plays
How the play was built
A man in motion.
Thrown on the first read.
FormationShotgunOffense on the fieldOne back, one tight end and three receiversDefense on the fieldFour linemen, two linebackers and five backsRoute runOutCoverageCover 6, quarter-quarter-halfMan or zoneZoneIn the boxSix defendersRushing the passerFourPressure (charted)The passer was pressuredTime to throw2.7 seconds
Browns9Commanders7
Browns10Commanders7
Touchdown7 plays, from the Browns 37 to the Commanders 46
Punt8 plays, from the Commanders 22 to midfield
How the play was built
Nobody in motion.
Thrown on the second read.
FormationShotgunOffense on the fieldOne back, one tight end and three receiversDefense on the fieldFour linemen, one linebacker and six backsRoute runCrosserCoverageCover 3, three deepMan or zoneZoneIn the boxSix defendersRushing the passerFivePressure (charted)The passer was kept cleanTime to throw2.9 seconds
Browns16Commanders7
Browns17Commanders7
Touchdown14 plays, from the Browns 16 to the Commanders 13
The period ended3 plays
4th quarter50 plays
Browns17Commanders10
Field goal8 plays, from the Commanders 29 to the Browns 24
Browns23Commanders10
Browns24Commanders10
Touchdown12 plays, from the Browns 25 to the Commanders 33
Intercepted9 plays, from the Commanders 25 to the Browns 40
The period ended7 plays, from the Browns 20 to the Browns 23
Turnover on downs7 plays, from the Commanders 36 to the Commanders 41
The period ended5 plays, from the Commanders 35 to the Commanders 34
The period ended2 plays
Win probability is the league play-by-play model, 98.5% of plays · a dash means none was published
