Today· Sep 17Pregame slateSettled· Sep 16

Regular season · week 2 · Sunday, Sep 20, 1:00 PM ET

Pittsburgh SteelersatNew England PatriotsEXPERIMENTAL

Gillette Stadium

Pittsburgh SteelersNew England PatriotsSaved on this device

59°F · 6 mph wind from the SE · 66% chance of rain · rain showers likely — 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.

PIT @ NE

Pittsburgh Steelers at New England Patriots at Gillette Stadium.

Simulation

What our model expects

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

Projected score

PIT 19 — 22 NE

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

Win chance

PIT 35.2% · NE 61.9%

how often each side won in 10,000 simulations · ties 2.9%

Total points (both teams)

8 in 10 simulations landed between 25 and 58

NE winning margin

a minus means PIT 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

PIT 19 — 22 NEwin chance PIT 35.2% · NE 61.9%total 41 (25–58)margin +3

PIT

Likely TD scorers

Jaylen Warren 41.0% · available role uncertain

Rico Dowdle 35.7% · available role uncertain

DK Metcalf 27.7% · available role uncertain

Passing

Aaron Rodgers 195 pass yds (108–320) · available role uncertain

Rushing leaders

Jaylen Warren 48 rush yds (12–127) · available role uncertain

Rico Dowdle 28 rush yds (5–86) · available role uncertain

New arrivals · not in these numbers

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

Rico Dowdle 2.1 rec · 16.9 yds/g at CAR

Michael Pittman Jr. 4.6 rec · 45.3 yds/g at IND

Receiving leaders

DK Metcalf 4 rec · 48 yds · available role uncertain

Rico Dowdle 3 rec · 24 yds · available role uncertain

Pat Freiermuth 3 rec · 26 yds · available role uncertain

Likely TD scorers

Rhamondre Stevenson 43.7% · available role uncertain

TreVeyon Henderson 31.8% · available role uncertain

Mack Hollins 22.5% · available role uncertain

Passing

Drake Maye 219 pass yds (121–360) · available role uncertain

Rushing leaders

Rhamondre Stevenson 42 rush yds (10–110) · available role uncertain

TreVeyon Henderson 31 rush yds (6–93) · available role uncertain

New arrivals · not in these numbers

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

A.J. Brown 5.1 rec · 64.3 yds/g at PHI

Romeo Doubs 3.4 rec · 44.7 yds/g at GB

Receiving leaders

Rhamondre Stevenson 3 rec · 32 yds · available role uncertain

Mack Hollins 3 rec · 38 yds · available role uncertain

DeMario Douglas 3 rec · 29 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)
Pittsburgh Steelers	8	19	31
New England Patriots	10	22	34

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 (PIT – NE)	Chance
17–20	1.04%
20–17	0.83%
24–27	0.68%
27–24	0.67%
20–24	0.60%
10–13	0.59%

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	11.2%	14.2%
Decided by exactly 7	7.2%	8.3%
Decided by exactly 10	5.9%	4.2%
Decided by exactly 14	5.1%	4.4%
Any of the four	29.4%	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.

PIT touchdowns

2.2

NE touchdowns

2.4

PIT field goals

1.5

NE field goals

1.6

Tied after regulation

4.3%

Comparison

Us versus the sportsbooks

two independent reads, shown side by side

No current sportsbook capture covers this game.

Player projections · 17 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
DK Metcalf	PIT	role uncertain	4 (1–9)	48 (17–103)	27.7%
Rhamondre Stevenson	NE	role uncertain	3 (1–7)	32 (8–74)	43.7%
Rico Dowdle	PIT	role uncertain	3 (1–6)	24 (4–60)	35.7%
Mack Hollins	NE	role uncertain	3 (1–7)	38 (11–87)	22.5%
DeMario Douglas	NE	role uncertain	3 (1–7)	29 (7–68)	20.5%
Hunter Henry	NE	role uncertain	3 (0–6)	27 (5–67)	19.0%
Pat Freiermuth	PIT	role uncertain	3 (0–6)	26 (4–65)	18.4%
Jaylen Warren	PIT	role uncertain	2 (0–6)	22 (3–56)	41.0%
Romeo Doubs	NE	role uncertain	2 (0–4)	17 (0–52)	14.6%
Roman Wilson	PIT	role uncertain	2 (0–5)	19 (0–53)	14.0%
Michael Pittman	PIT	questionable	2 (0–4)	16 (0–49)	11.1%
Darnell Washington	PIT	role uncertain	2 (0–4)	15 (0–47)	10.3%
TreVeyon Henderson	NE	role uncertain	1 (0–3)	8 (0–34)	31.8%
Lan Larison	NE	role uncertain	1 (0–3)	10 (0–38)	9.6%

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)
A.J. Brown WR	NE	out	PHI · 16g	5.1 rec · 64.3 yds
Romeo Doubs WR	NE	active uncertain	GB · 19g	3.4 rec · 44.7 yds
Rico Dowdle RB	PIT	active uncertain	CAR · 20g	2.1 rec · 16.9 yds · 54.7 rush yds
Michael Pittman Jr. WR	PIT	questionable	IND · 18g	4.6 rec · 45.3 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 17 by TD chance · full list in the board’s TD tab

43.7% Rhamondre Stevenson · NE · available role uncertain
41.0% Jaylen Warren · PIT · available role uncertain
35.7% Rico Dowdle · PIT · available role uncertain
31.8% TreVeyon Henderson · NE · available role uncertain
27.7% DK Metcalf · PIT · available role uncertain
22.5% Mack Hollins · NE · 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: c1a0b434083981a2
generated: 2026-09-17T14:17:00Z
kickoff: 2026-09-20T17:00Z
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.