PIT @ NE
Pittsburgh Steelers at New England Patriots, Sun, Sep 20. This game has been played — what follows is the forecast as it was frozen BEFORE kickoff, not a current read.
Regular season · week 2 · Sunday, Sep 20, 1:00 PM ET · final
Pittsburgh Steelers at New England Patriots
Archived pregame read · published before kickoff. Everything below is the forecast revision the graded record names, read from its committed file and not regenerated. The final was PIT 3 – 20 NE, from the Week 2 record.
What happened · official box score
Final: PIT 3 – 20 NE
The played game's official lines, recorded Sep 20, 2026, the same lines the forecasts on this page were graded against. Under each actual is the Official Forecast published before kickoff, with its 80% range.
Pittsburgh Steelers · 3
| Player | Pass yds | Rush yds | Rec | Rec yds | TD |
|---|---|---|---|---|---|
| Aaron Rodgers | 187Forecast 195 (108–320) · in range | 5Forecast 2 (0–25) · in range | 0 | 0 | NoForecast 6.9% |
| Jaylen Warren | 0 | 43Forecast 48 (12–127) · in range | 2Forecast 2 (0–6) · in range | 34Forecast 22 (3–56) · in range | NoForecast 41.0% |
| Rico Dowdle | 0 | 22Forecast 28 (5–86) · in range | 2Forecast 3 (1–6) · in range | 22Forecast 24 (4–60) · in range | NoForecast 35.7% |
| Germie Bernard | 0 | 0 | 4 | 35 | No |
| Pat Freiermuth | 0 | 2 | 4Forecast 3 (0–6) · in range | 32Forecast 26 (4–65) · in range | NoForecast 18.4% |
| Roman Wilson | 0 | 0 | 5Forecast 2 (0–5) · in range | 28Forecast 19 (0–53) · in range | NoForecast 14.0% |
| DK Metcalf | 0 | 0 | 4Forecast 4 (1–9) · in range | 27Forecast 48 (17–103) · in range | NoForecast 27.7% |
| Travis Homer | 0 | 16 | 0 | 0 | No |
| Darnell Washington | 0 | 0 | 1Forecast 2 (0–4) · in range | 7Forecast 15 (0–47) · in range | NoForecast 10.3% |
| Mason Rudolph | 0 | 3 | 0 | 0 | No |
| Ben Skowronek | 0 | 0 | 1 | 2 | No |
| Player lines added up | 187 | 91 | 23 | 187 |
21 other Pittsburgh Steelers players appear in the official box score with no passing, rushing or receiving line.
New England Patriots · 20
| Player | Pass yds | Rush yds | Rec | Rec yds | TD |
|---|---|---|---|---|---|
| Drake Maye | 208Forecast 219 (121–360) · in range | 17Forecast 20 (2–76) · in range | 0 | 0 | NoForecast 16.6% |
| Romeo Doubs | 0 | 0 | 3Forecast 2 (0–4) · in range | 96Forecast 17 (0–52) · outside range | NoForecast 14.6% |
| TreVeyon Henderson | 0 | 76Forecast 31 (6–93) · in range | 0Forecast 1 (0–3) · in range | 0Forecast 8 (0–34) · in range | YesForecast 31.8% |
| Rhamondre Stevenson | 0 | 43Forecast 42 (10–110) · in range | 1Forecast 3 (1–7) · in range | 3Forecast 32 (8–74) · outside range | NoForecast 43.7% |
| Hunter Henry | 0 | 0 | 3Forecast 3 (0–6) · in range | 40Forecast 27 (5–67) · in range | NoForecast 19.0% |
| Eli Raridon | 0 | 0 | 1 | 30 | No |
| Mack Hollins | 0 | 0 | 2Forecast 3 (1–7) · in range | 18Forecast 38 (11–87) · in range | NoForecast 22.5% |
| Kyle Williams | 0 | 0 | 1 | 10 | No |
| DeMario Douglas | 0 | 0 | 1Forecast 3 (1–7) · in range | 9Forecast 29 (7–68) · in range | NoForecast 20.5% |
| Reggie Gilliam | 0 | 0 | 1 | 4 | No |
| Corey Kiner | 0 | 0Forecast 12 (1–53) · outside range | 0 | 0 | NoForecast 13.5% |
| Elijah Ponder | 0 | 0 | 0 | 0 | Yes |
| Lan LarisonNo line in the official box score | — | — | —Forecast 1 (0–3) | —Forecast 10 (0–38) | —Forecast 9.6% |
| Efton Chism III | 0 | 0 | 1 | -2 | No |
| Player lines added up | 208 | 136 | 14 | 208 |
23 other New England Patriots players appear in the official box score with no passing, rushing or receiving line.
Shown: the passing, rushing and receiving lines and touchdowns GameTimePicks records; defensive and kicking statistics are not recorded here. “Player lines added up” sums the players' lines, so team passing yards are before sack yardage. TD means a rushing, receiving, return or recovery touchdown; a thrown one does not count. “—” means the player has no line in the official box score. Every graded forecast for Week 2 is on the NFL week report.
Regular season · week 2 · Sunday, Sep 20, 1:00 PM ET · Gillette Stadium
Pittsburgh Steelers at New England Patriots
Pittsburgh Steelers35.3% to winPregame projection
19–22
the middle of the outcomes, not a call on the exact final
New England Patriots61.9% to winNew England Patriots were the projected winner, 61.9% to win.
About 3% chance of a tie after regulation is not assigned to either team.
Expected margin
NE +3
8 in 10 outcomes between -14 and +19
Expected total
41
8 in 10 outcomes between 25 and 59
Official Forecast · frozen before kickoff · graded after
The authorized GameTimePicks output for a game or player, frozen before the start and never edited afterwards. Each one is graded against the official result once the game is final, and results are published as games are graded. Player results grade the official player board's own pre-kickoff projections, each under the model and version that made it — the same projections the game pages and Weekly leaders show. The supporting simulations some game pages show are not graded in these results, so none of these results describe them.
Simulation story
5 chapters · the forecast as it stood before the start› 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.
Projected scorecard
expected statistical summaries · not one simulated gamePIT 19 — 22 NEwin chance PIT 35.3% · NE 61.9%total 41 (25–59)margin +3
PIT
Likely TD scorers
Jaylen Warren 41.0%
Rico Dowdle 35.7%
DK Metcalf 27.7%
Passing
Aaron Rodgers 195 pass yds (108–320)
Rushing leaders
Jaylen Warren 48 rush yds (12–127)
Rico Dowdle 28 rush yds (5–86)
Receiving leaders
DK Metcalf 4 rec · 48 yds
Rico Dowdle 3 rec · 24 yds
Pat Freiermuth 3 rec · 26 yds
NE
Likely TD scorers
Rhamondre Stevenson 43.7%
TreVeyon Henderson 31.8%
Mack Hollins 22.5%
Passing
Drake Maye 219 pass yds (121–360)
Rushing leaders
Rhamondre Stevenson 42 rush yds (10–110)
TreVeyon Henderson 31 rush yds (6–93)
Receiving leaders
Rhamondre Stevenson 3 rec · 32 yds
Mack Hollins 3 rec · 38 yds
DeMario Douglas 3 rec · 29 yds
pass interceptions · First/last/2+ touchdown — withheld, with the exact bar each failed
- pass interceptions: research only, not published as a forecast
- First/last/2+ touchdown: DISABLED — no ordering model and no calibration receipt of their own; never derived from anytime probabilities
Comparison
Us versus the sportsbooks
two independent reads, shown side by side
Our win chance
61.9%
NE to win
Sportsbook win chance
67.8%
NE to win, read from 9 sportsbooks' odds with their built-in margin removed
Difference
-5.9 pp
ours minus the sportsbooks', in percentage points — not a recommendation
Total points: ours vs sportsbooks
41 vs 41.5
our projected total against the sportsbooks' over/under line
The sportsbook numbers are the books' own, shown for context. A difference is a difference — this model is not validated to out-predict the sportsbook market.
Prices captured — before kickoff.
Player projections · 16 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 median receptions.
| Player | Team | Availability | Receptions (10th–90th) | Rec yards (10th–90th) | TD chance |
|---|---|---|---|---|---|
| DK Metcalf | PIT | 4 (1–9) | 48 (17–103) | 27.7% | |
| Rhamondre Stevenson | NE | 3 (1–7) | 32 (8–74) | 43.7% | |
| Rico Dowdle | PIT | 3 (1–6) | 24 (4–60) | 35.7% | |
| Mack Hollins | NE | 3 (1–7) | 38 (11–87) | 22.5% | |
| DeMario Douglas | NE | 3 (1–7) | 29 (7–68) | 20.5% | |
| Hunter Henry | NE | 3 (0–6) | 27 (5–67) | 19.0% | |
| Pat Freiermuth | PIT | 3 (0–6) | 26 (4–65) | 18.4% | |
| Jaylen Warren | PIT | 2 (0–6) | 22 (3–56) | 41.0% | |
| Romeo Doubs | NE | 2 (0–4) | 17 (0–52) | 14.6% | |
| Roman Wilson | PIT | 2 (0–5) | 19 (0–53) | 14.0% | |
| Darnell Washington | PIT | 2 (0–4) | 15 (0–47) | 10.3% | |
| TreVeyon Henderson | NE | 1 (0–3) | 8 (0–34) | 31.8% | |
| Lan Larison | NE | 1 (0–3) | 10 (0–38) | 9.6% |
Families not shown, and the exact bar each failed (2)
- pass interceptions: research only, not published as a forecast
- First/last/2+ touchdown: DISABLED — no ordering model and no calibration receipt of their own; never derived from anytime probabilities
Scoring outlooktop 6 of 16 by TD chance · full list in the board’s TD tab
- 43.7% Rhamondre Stevenson · NE
- 41.0% Jaylen Warren · PIT
- 35.7% Rico Dowdle · PIT
- 31.8% TreVeyon Henderson · NE
- 27.7% DK Metcalf · PIT
- 22.5% Mack Hollins · NE
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
- The model's chance for each side to win, from its team-strength rating — not a count of simulated wins. The simulated games show their own win share, and the difference, in Simulated game outcomes.
- 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.
- Official Forecast
- The authorized GameTimePicks output for a game or player, frozen before the start and never edited afterwards. Each one is graded against the official result; its record on games played after it was frozen is still accumulating.
Technical detailsModel version, input fingerprint, timestamps and the per-family evaluation basis.
Where this came from
- model
- nfl-regular-season-public-v1 v2
- simulations
- 10,000
- input hash
- 9e1540a66f0ee0dd
- generated
- kickoff
- state
- SETTLED
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. These ratings are built from results, not from who is playing: they do not know that a starting quarterback has been ruled out. Our player projections do remove players who cannot play; the team win chance beside them does not. We tested whether adding that would help, using perfect hindsight about whether each team's main quarterback actually played — on 855 games from 2023 to 2025 it improved the win rating on average but was WORSE in one of the three seasons, so it did not clear the bar we hold these ratings to and we left the rating alone.
Educational and paper-only — not betting advice.
More
Other games with a simulation
- CAR @ GBThursday, Oct 29, 8:15 PM ET
- ARI @ DALSunday, Nov 1, 1:00 PM ET
- ATL @ TBSunday, Nov 1, 1:00 PM ET
- BAL @ BUFSunday, Nov 1, 1:00 PM ET
- CLE @ PITSunday, Nov 1, 1:00 PM ET
- IND @ JAXSunday, Nov 1, 1:00 PM ET
- LV @ NYJSunday, Nov 1, 1:00 PM ET
- MIN @ DETSunday, Nov 1, 1:00 PM ET
- TEN @ CINSunday, Nov 1, 1:00 PM ET
- LAC @ LARSunday, Nov 1, 4:05 PM ET
- KC @ DENSunday, Nov 1, 4:25 PM ET
- NE @ MIASunday, Nov 1, 4:25 PM ET
- PHI @ WSHSunday, Nov 1, 8:20 PM ET
- CHI @ SEAMonday, Nov 2, 8:15 PM ET