Today· Sep 17Pregame slateSettled· Sep 16

Regular season · week 2 · Sunday, Sep 20, 4:25 PM ET

Washington CommandersatDallas CowboysEXPERIMENTAL

AT&T Stadium

Washington CommandersDallas CowboysSaved on this device

99°F · 5 mph wind from the S · 0% chance of rain · mostly sunny — the schedule carries no roof for this stadium, so this is the open-air forecast — not used by the model; no weather term enters the numbers below.

Simulation story

5 chapters · read from the published artifact

Skip to the report ↓

› Loading the matchup model› Reading the outcome distribution from 10,000 simulated games› Preparing the score scenariosPress Play to step through what the model expects, chapter by chapter, or read the report below.

WSH @ DAL

Washington Commanders at Dallas Cowboys at AT&T Stadium.

Simulation

What our model expects

10,000 simulated games · model nfl-regular-season-public-v1

Projected score

WSH 25 — 29 DAL

the middle of our simulated outcomes, not a call on the exact final

Win chance

WSH 46.2% · DAL 51.0%

how often each side won in 10,000 simulations · ties 2.8%

Total points (both teams)

8 in 10 simulations landed between 37 and 71

DAL winning margin

a minus means WSH wins by that much · 8 in 10 between -14 and 19

Model details

From the margin-of-victory Elo win head, published exactly as evaluated on held-out 2006–2021 — no shrink toward 50% is applied, and no claim to out-predict the sportsbook market is made. Generated 2026-09-17T14:17:00Z under model nfl-regular-season-public-v1 and frozen pre-kickoff; every forecast is settled against the official result.

Projected scorecard

expected statistical summaries · not one simulated game

WSH 25 — 29 DALwin chance WSH 46.2% · DAL 51.0%total 54 (37–71)margin +3

WSH

Likely TD scorers

Jacory Croskey-Merritt 40.7% · available role uncertain

Stefon Diggs 40.4% · available role uncertain

Terry McLaurin 25.4% · available role uncertain

Passing

Jayden Daniels 179 pass yds (95–303) · available role uncertain

Rushing leaders

Jacory Croskey-Merritt 41 rush yds (10–111) · available role uncertain

Jayden Daniels 18 rush yds (2–70) · available role uncertain

New arrivals · not in these numbers

Per game at their previous club — history, not a projection.

Rachaad White 2.2 rec · 12.1 yds/g at TB

Stefon Diggs 4.7 rec · 53.5 yds/g at NE

Chig Okonkwo 3.2 rec · 31.7 yds/g at TEN

Receiving leaders

Stefon Diggs 6 rec · 66 yds · available role uncertain

Terry McLaurin 4 rec · 39 yds · available role uncertain

Antonio Williams 3 rec · 30 yds · available role uncertain

DAL

Likely TD scorers

Javonte Williams 57.0% · available role uncertain

CeeDee Lamb 35.0% · available role uncertain

George Pickens 28.2% · available role uncertain

Passing

Dak Prescott 209 pass yds (116–344) · available role uncertain

Rushing leaders

Javonte Williams 55 rush yds (15–137) · available role uncertain

Emari Demercado 5 rush yds (0–40) · available role uncertain

Receiving leaders

CeeDee Lamb 5 rec · 53 yds · available role uncertain

George Pickens 4 rec · 47 yds · available role uncertain

Ryan Flournoy 3 rec · 28 yds · available role uncertain

pass interceptions · First/last/2+ touchdown — withheld, with the exact bar each failed

pass interceptions: RESEARCH_ONLY
First/last/2+ touchdown: DISABLED — no ordering model and no calibration receipt of their own; never derived from anytime probabilities

Range

How wide the outcomes are

the 10th to 90th percentile of each team's simulated score

Team	Low (10th)	Projected	High (90th)
Washington Commanders	14	25	38
Dallas Cowboys	17	29	41

Exact score

The likeliest final scores

from an event-based simulation of touchdowns and field goals, solved onto the median margin and total above

Score (WSH – DAL)	Chance
24–27	0.67%
27–30	0.66%
27–24	0.63%
20–23	0.63%
23–20	0.52%
30–27	0.49%

No single scoreline is likely — these are the most common of hundreds. The projected score above is derived from the medians and answers a different question: the middle of the distribution, not its most common point.

Key numbers

How often it lands on 3, 7, 10 or 14

football's margins pile up on those four — this is the one thing a normal-draw model cannot show you

Margin	This game	Last 3 regular seasons
Decided by exactly 3	9.7%	14.2%
Decided by exactly 7	6.2%	8.3%
Decided by exactly 10	5.0%	4.2%
Decided by exactly 14	4.5%	4.4%
Any of the four	25.3%	31.1%

The right-hand column is what actually happened across 816 regular-season games (2023, 2024, 2025) — the same finals this engine was fitted to. It gets the shape right, with 3 the most common margin by a distance, and it is not calibrated to the number: it puts less weight on 3 and more on 10 than those seasons did.

WSH touchdowns

2.8

DAL touchdowns

3.1

WSH field goals

1.9

DAL field goals

2.1

Tied after regulation

3.6%

Comparison

Us versus the sportsbooks

two independent reads, shown side by side

No current sportsbook capture covers this game.

Player projections · 25 modelled

The player board

Every modelled player, with his availability. Players listed out carry no volume projection.

Every receiving family for one player on one row, ranked by expected receptions.

Player	Team	Availability	Receptions (10th–90th)	Rec yards (10th–90th)	TD chance
Stefon Diggs	WSH	role uncertain	6 (2–12)	66 (27–129)	40.4%
CeeDee Lamb	DAL	role uncertain	5 (1–10)	53 (20–109)	35.0%
George Pickens	DAL	role uncertain	4 (1–8)	47 (16–103)	28.2%
Terry McLaurin	WSH	role uncertain	4 (1–8)	39 (12–89)	25.4%
Antonio Williams	WSH	role uncertain	3 (1–6)	30 (6–74)	21.8%
Ryan Flournoy	DAL	role uncertain	3 (1–6)	28 (5–69)	20.4%
Javonte Williams	DAL	role uncertain	2 (0–5)	21 (3–54)	57.0%
Treylon Burks	WSH	role uncertain	2 (0–6)	26 (4–65)	19.2%
Jeremy McNichols	WSH	role uncertain	2 (0–4)	14 (0–45)	17.8%
Jake Ferguson	DAL	role uncertain	2 (0–5)	19 (0–51)	16.1%
Chig Okonkwo	WSH	questionable	2 (0–5)	18 (0–51)	14.1%
Rachaad White	WSH	role uncertain	1 (0–4)	11 (0–37)	24.3%
John Bates	WSH	role uncertain	1 (0–4)	12 (0–40)	10.7%
KaVontae Turpin	DAL	role uncertain	1 (0–3)	8 (0–35)	9.9%
Luke McCaffrey	WSH	role uncertain	1 (0–3)	10 (0–39)	9.7%
Dyami Brown	WSH	role uncertain	1 (0–3)	10 (0–38)	9.7%
Brevyn Spann-Ford	DAL	role uncertain	1 (0–3)	8 (0–34)	8.2%

New arrivals · not in the simulated numbers above

Per game at their previous team — history, not a projection.

Player	Team	Availability	Last club	Per game (prior club)
Rachaad White RB	WSH	active uncertain	TB · 18g	2.2 rec · 12.1 yds · 33.3 rush yds
Stefon Diggs WR	WSH	active uncertain	NE · 21g	4.7 rec · 53.5 yds
Chig Okonkwo TE	WSH	questionable	TEN · 18g	3.2 rec · 31.7 yds
Dyami Brown WR	WSH	active uncertain	JAX · 12g	1.7 rec · 18.9 yds
Van Jefferson WR	WSH	active uncertain	TEN · 17g	1.9 rec · 26.6 yds

Families not shown, and the exact bar each failed (2)

pass interceptions: RESEARCH_ONLY
First/last/2+ touchdown: DISABLED — no ordering model and no calibration receipt of their own; never derived from anytime probabilities

Scoring outlooktop 6 of 25 by TD chance · full list in the board’s TD tab

57.0% Javonte Williams · DAL · available role uncertain
40.7% Jacory Croskey-Merritt · WSH · available role uncertain
40.4% Stefon Diggs · WSH · available role uncertain
35.0% CeeDee Lamb · DAL · available role uncertain
28.2% George Pickens · DAL · available role uncertain
25.4% Terry McLaurin · WSH · available role uncertain

Anytime-scorer probability means scoring a touchdown — never throwing one. Void if the player does not play; questionable players carry their state above.

Reading key

What these numbers mean

Projected score: The middle outcome across every simulated game — not a prediction of the exact final.
Win chance: How often each side won across the simulations, after the calibration described above.
80% range: Eight in ten simulated games landed inside this band. Real games land outside it too.
pp (percentage points): The plain difference between two percentages. A gap is a difference, not an advantage.
Experimental: Published while its out-of-sample record is still accumulating. Every forecast is frozen before kickoff and graded against the official result.

Provenance

Where this came from

model: nfl-regular-season-public-v1 v2
simulations: 10,000
input hash: 15a46ec05237c84f
generated: 2026-09-17T14:17:00Z
kickoff: 2026-09-20T20:25Z
state: UPCOMING

Player-family model provenance (4 published)

Rushing yards: Share-level model: cleared every bar when re-tested on 2014–2021 (14,502 player-games) — a second look at seasons examined once before, not a blind test. Each week's forecast is frozen before the first kickoff and graded; its blind 2026 record is still accumulating (0 graded player-games so far).
Receiving yards: Share-level model: cleared every bar when re-tested on 2014–2021 (27,134 player-games) — a second look at seasons examined once before, not a blind test. Each week's forecast is frozen before the first kickoff and graded; its blind 2026 record is still accumulating (0 graded player-games so far).
Receptions: Share-level model: cleared every bar when re-tested on 2014–2021 (27,134 player-games) — a second look at seasons examined once before, not a blind test. Each week's forecast is frozen before the first kickoff and graded; its blind 2026 record is still accumulating (0 graded player-games so far).
Anytime touchdown: Opportunity touchdown model: cleared every bar on a blind test of 2014–2021 (35,128 player-games never used to build it). Probabilities condition on playing — a player who does not play settles void. Each week's forecast is frozen before the first kickoff and graded; its blind 2026 record is still accumulating (0 graded player-games so far).

Our win chances come from a team rating that weights how decisively teams win. Tested on 4,281 past games it had never seen (2006–2021), it scored 0.629 on log loss (lower is better) — better than our previous rating's 0.642 and a coin flip's 0.693, but short of the sportsbooks' own odds at 0.610. It has NOT been shown to beat the sportsbook market. Where our win and margin ratings disagree on the favourite, the previous rating is used for that game. The 2026 season evaluation still runs under bars frozen in August, so every forecast stays experimental.

Educational and paper-only — not betting advice.