GridironProjector NFL

Scorecard

Our last number before kickoff, graded against the final score and the closing line.

2026 season only

Frozen pregame record

A scheduled job saves the model's current number for every upcoming game (at most once an hour, with the market line at that moment) and stops at kickoff. Each game below is graded from the last number saved before it kicked off, so the result could never have changed it. Closing line = the last market consensus this site stored before kickoff, else the nflverse closing line. 15 upcoming games have a snapshot; newest Oct 29, 12:21 AM ET.

49/73
Times we named the right winner
8.5
Points off on the margin
10.8
Points off on the total

Closing line, same games: 45/73 winners · 8.3 points off the margin · 10.4 off the total (74 games with a recorded closing line).

Our margin was closer to the final than the closing line in 49% of games; on average our number sat 1.9 points from the closing line. Brier score 0.228 (0.250 = coin flip).

Our total vs what they scored

Games that went over our total
happened 39 out of 74 games (53%)
over a long run, expect somewhere between 41% and 64%
Games that stayed under it
happened 35 out of 74 games (47%)
over a long run, expect somewhere between 36% and 59%

When we said the total would be Under 40 points

5 games · we said 39.2 on average · they really scored 43.8

Finished over our total
happened 4 out of 5 games (80%)
over a long run, expect somewhere between 38% and 96%
Finished under our total
happened 1 out of 5 games (20%)
over a long run, expect somewhere between 4% and 62%

When we said the total would be 40 to 43.9 points

21 games · we said 42.4 on average · they really scored 40.0

Finished over our total
happened 7 out of 21 games (33%)
over a long run, expect somewhere between 17% and 55%
Finished under our total
happened 14 out of 21 games (67%)
over a long run, expect somewhere between 45% and 83%

When we said the total would be 44 to 47.9 points

29 games · we said 45.6 on average · they really scored 49.0

Finished over our total
happened 18 out of 29 games (62%)
over a long run, expect somewhere between 44% and 77%
Finished under our total
happened 11 out of 29 games (38%)
over a long run, expect somewhere between 23% and 56%

When we said the total would be 48 to 51.9 points

12 games · we said 50.6 on average · they really scored 46.9

Finished over our total
happened 5 out of 12 games (42%)
over a long run, expect somewhere between 19% and 68%
Finished under our total
happened 7 out of 12 games (58%)
over a long run, expect somewhere between 32% and 81%

When we said the total would be 52 to 55.9 points

7 games · we said 53.7 on average · they really scored 56.6

Finished over our total
happened 5 out of 7 games (71%)
over a long run, expect somewhere between 36% and 92%
Finished under our total
happened 2 out of 7 games (29%)
over a long run, expect somewhere between 8% and 64%

Our winning margin vs the real one

When we projected A win by less than 3

33 games · we said the winner would win by 1.4 · the real margin was 9.0

Won by more than we said
happened 33 out of 33 games (100%)
over a long run, expect somewhere between 90% and 100%
Won by less, or lost
happened 0 out of 33 games (0%)
over a long run, expect somewhere between 0% and 10%

Right winner in 21 out of 33 of them (over a long run, expect between 47% and 78%).

When we projected A win by 3 to 6.9

25 games · we said the winner would win by 4.6 · the real margin was 10.2

Won by more than we said
happened 18 out of 25 games (72%)
over a long run, expect somewhere between 52% and 86%
Won by less, or lost
happened 7 out of 25 games (28%)
over a long run, expect somewhere between 14% and 48%

Right winner in 17 out of 24 of them (over a long run, expect between 51% and 85%).

When we projected A win by 7 to 10.9

12 games · we said the winner would win by 9.1 · the real margin was 6.8

Won by more than we said
happened 2 out of 12 games (17%)
over a long run, expect somewhere between 5% and 45%
Won by less, or lost
happened 10 out of 12 games (83%)
over a long run, expect somewhere between 55% and 95%

Right winner in 8 out of 12 of them (over a long run, expect between 39% and 86%).

When we projected A win by 11 to 13.9

4 games · we said the winner would win by 12.1 · the real margin was 4.8

Won by more than we said
happened 0 out of 4 games (0%)
over a long run, expect somewhere between 0% and 49%
Won by less, or lost
happened 4 out of 4 games (100%)
over a long run, expect somewhere between 51% and 100%

Right winner in 3 out of 4 of them (over a long run, expect between 30% and 95%).

Every graded game

DAL@PHI

Week 7 · we said PHI by 2.3, total 46.2 · close DAL by 4.5, 44

Frozen Oct 26, 7:52 PM ET

38–21
Wrong winner
KC@SEA

Week 7 · we said SEA by 3.5, total 43.1 · close SEA by 3.0, 42.5

Frozen Oct 25, 7:52 PM ET

3–20
Right winner
GB@DET

Week 7 · we said DET by 4.5, total 54.5 · close DET by 3.5, 55.5

Frozen Oct 25, 4:12 PM ET

17–20
Right winner
LA@LV

Week 7 · we said LA by 2.0, total 49.9 · close LA by 3.5, 48.5

Frozen Oct 25, 4:12 PM ET

35–21
Right winner
DEN@ARI

Week 7 · we said DEN by 5.0, total 44.7 · close DEN by 4.5, 43.5

Frozen Oct 25, 3:52 PM ET

30–16
Right winner
SF@ATL

Week 7 · we said SF by 5.6, total 50.4 · close SF by 2.5, 50.5

Frozen Oct 25, 12:53 PM ET

20–29
Wrong winner
CLE@TEN

Week 7 · we said CLE by 2.8, total 37.2 · close CLE by 2.0, 36.5

Frozen Oct 25, 12:53 PM ET

27–24
Right winner
IND@MIN

Week 7 · we said MIN by 9.7, total 43.5 · close MIN by 6.5, 41.5

Frozen Oct 25, 12:53 PM ET

10–16
Right winner
MIA@NYJ

Week 7 · we said NYJ by 3.8, total 40.9 · close NYJ by 4.0, 39.5

Frozen Oct 25, 12:53 PM ET

28–25
Wrong winner
TB@CAR

Week 7 · we said CAR by 6.7, total 44.5 · close CAR by 3.0, 44.5

Frozen Oct 25, 12:53 PM ET

43–13
Wrong winner
CIN@BAL

Week 7 · we said CIN by 2.1, total 47.3 · close CIN by 3.0, 46.5

Frozen Oct 25, 12:53 PM ET

35–13
Right winner
NYG@HOU

Week 7 · we said HOU by 9.9, total 43.7 · close HOU by 10.5, 42.5

Frozen Oct 25, 12:53 PM ET

27–21
Wrong winner
PIT@NO

Week 7 · we said PIT by 3.3, total 44.1 · close PIT by 3.0, 43.5

Frozen Oct 25, 9:17 AM ET

16–10
Right winner
NE@CHI

Week 7 · we said CHI by 1.1, total 48.4 · close CHI by 3.0, 50.5

Frozen Oct 22, 8:13 PM ET

24–30
Right winner
WAS@SF

Week 6 · we said SF by 9.0, total 51.9 · close SF by 7.5, 51.5

Frozen Oct 19, 7:52 PM ET

17–23
Right winner
DAL@GB

Week 6 · we said GB by 3.0, total 52.7 · close GB by 1.0, 53.5

Frozen Oct 18, 7:52 PM ET

13–23
Right winner
LAC@KC

Week 6 · we said KC by 9.2, total 41.8 · close KC by 7.5, 41.5

Frozen Oct 18, 3:52 PM ET

6–22
Right winner
BUF@LV

Week 6 · we said BUF by 4.8, total 54.5 · close BUF by 5.0, 53.5

Frozen Oct 18, 3:52 PM ET

33–30
Right winner
ARI@LA

Week 6 · we said LA by 11.6, total 51.8 · close LA by 12.5, 51.5

Frozen Oct 18, 3:52 PM ET

18–16
Wrong winner
CHI@ATL

Week 6 · we said CHI by 0.5, total 49.0 · close CHI by 1.0, 52.5

Frozen Oct 18, 12:52 PM ET

31–23
Right winner
BAL@CLE

Week 6 · we said CLE by 0.9, total 40.7 · close BAL by 3.0, 39.5

Frozen Oct 18, 12:52 PM ET

10–13
Right winner
TEN@IND

Week 6 · we said IND by 10.4, total 45.1 · close IND by 6.5, 44.5

Frozen Oct 18, 12:52 PM ET

26–20
Wrong winner
NYJ@NE

Week 6 · we said NE by 10.3, total 43.5 · close NE by 7.5, 43.5

Frozen Oct 18, 12:52 PM ET

19–26
Right winner
NO@NYG

Week 6 · we said NYG by 2.2, total 45.5 · close NO by 1.0, 45.5

Frozen Oct 18, 12:52 PM ET

34–27
Wrong winner
CAR@PHI

Week 6 · we said CAR by 0.7, total 41.7 · close CAR by 3.0, 39

Frozen Oct 18, 12:52 PM ET

25–14
Right winner
PIT@TB

Week 6 · we said PIT by 0.5, total 39.4 · close PIT by 2.5, 38.5

Frozen Oct 18, 12:52 PM ET

26–19
Right winner
HOU@JAX

Week 6 · we said JAX by 3.7, total 41.6 · close JAX by 2.5, 42.5

Frozen Oct 18, 9:17 AM ET

34–31
Wrong winner
SEA@DEN

Week 6 · we said SEA by 1.0, total 40.7 · close SEA by 3.0, 40.5

Frozen Oct 15, 7:51 PM ET

14–17
Wrong winner
BUF@LA

Week 5 · we said LA by 1.1, total 54.2 · close LA by 3.5, 54.5

Frozen Oct 12, 7:54 PM ET

37–34
Wrong winner
BAL@ATL

Week 5 · we said ATL by 4.2, total 44.9 · close ATL by 3.5, 43.5

Frozen Oct 11, 7:53 PM ET

30–23
Wrong winner
DET@ARI

Week 5 · we said DET by 3.5, total 54.7 · close DET by 5.5, 54.5

Frozen Oct 11, 3:53 PM ET

45–21
Right winner
SF@SEA

Week 5 · we said SEA by 1.4, total 46.7 · close SEA by 3.0, 46.5

Frozen Oct 11, 3:53 PM ET

32–29
Wrong winner
DEN@LAC

Week 5 · we said DEN by 1.5, total 43.9 · close DEN by 3.5, 42

Frozen Oct 11, 3:53 PM ET

23–17
Right winner
CHI@GB

Week 5 · we said GB by 0.6, total 44.6 · close CHI by 1.5, 46.5

Frozen Oct 11, 12:55 PM ET

7–31
Right winner
HOU@TEN

Week 5 · we said HOU by 5.5, total 41.9 · close HOU by 7.0, 37.5

Frozen Oct 11, 12:55 PM ET

26–3
Right winner
CIN@MIA

Week 5 · we said CIN by 5.3, total 46.6 · close CIN by 7.0, 43.5

Frozen Oct 11, 12:55 PM ET

31–24
Right winner
LV@NE

Week 5 · we said NE by 4.3, total 44.6 · close NE by 3.5, 45

Frozen Oct 11, 12:55 PM ET

17–45
Right winner
MIN@NO

Week 5 · we said MIN by 5.5, total 45.0 · close MIN by 2.5, 41.5

Frozen Oct 11, 12:55 PM ET

23–13
Right winner
CLE@NYJ

Week 5 · we said NYJ by 0.2, total 41.3 · close NYJ by 2.5, 39.5

Frozen Oct 11, 12:55 PM ET

12–17
Right winner
IND@PIT

Week 5 · we said PIT by 1.8, total 46.4 · close PIT by 3.0, 43.5

Frozen Oct 11, 12:55 PM ET

22–34
Right winner
NYG@WAS

Week 5 · we said WAS by 4.4, total 44.0 · close WAS by 3.5, 41.5

Frozen Oct 11, 12:55 PM ET

27–27
Tie
PHI@JAX

Week 5 · we said JAX by 7.6, total 42.7 · close JAX by 8.0, 41.5

Frozen Oct 11, 9:20 AM ET

17–19
Right winner
TB@DAL

Week 5 · we said DAL by 7.8, total 51.3 · close DAL by 8.5, 47.5

Frozen Oct 8, 7:53 PM ET

24–16
Wrong winner
ATL@NO

Week 4 · we said NO by 2.9, total 47.6 · close NO by 2.0, 47.5

Frozen Oct 5, 7:52 PM ET

45–24
Wrong winner
DET@CAR

Week 4 · we said DET by 1.4, total 52.3 · close DET by 4.0, 51

Frozen Oct 4, 7:52 PM ET

26–32
Wrong winner
KC@LV

Week 4 · we said KC by 2.4, total 47.2 · close KC by 4.5, 47.5

Frozen Oct 4, 4:16 PM ET

30–27
Right winner
DEN@SF

Week 4 · we said SF by 5.7, total 48.6 · close SF by 2.5, 48

Frozen Oct 4, 4:16 PM ET

14–24
Right winner
LAC@SEA

Week 4 · we said SEA by 9.2, total 39.9 · close SEA by 7.0, 43

Frozen Oct 4, 4:16 PM ET

23–30
Right winner
MIA@MIN

Week 4 · we said MIN by 11.9, total 42.9 · close MIN by 10.0, 38.5

Frozen Oct 4, 1:45 PM ET

10–15
Right winner
NE@BUF

Week 4 · we said BUF by 4.7, total 45.7 · close BUF by 7.0, 49.5

Frozen Oct 4, 11:30 AM ET

29–26
Wrong winner
NYJ@CHI

Week 4 · we said CHI by 5.7, total 45.0 · close CHI by 3.5, 43.5

Frozen Oct 4, 11:30 AM ET

12–23
Right winner
JAX@CIN

Week 4 · we said JAX by 1.6, total 47.8 · close CIN by 2.5, 51.5

Frozen Oct 4, 11:30 AM ET

22–17
Right winner
ARI@NYG

Week 4 · we said ARI by 0.7, total 43.6 · close ARI by 2.5, 44.5

Frozen Oct 4, 11:30 AM ET

24–36
Wrong winner
LA@PHI

Week 4 · we said LA by 2.5, total 44.9 · close LA by 3.5, 42.5

Frozen Oct 4, 11:30 AM ET

24–20
Right winner
GB@TB

Week 4 · we said GB by 2.7, total 44.2 · close GB by 3.0, 39

Frozen Oct 4, 11:30 AM ET

17–14
Right winner
TEN@BAL

Week 4 · we said BAL by 13.2, total 45.4 · close BAL by 11.5, 42.5

Frozen Oct 4, 11:30 AM ET

18–24
Right winner
DAL@HOU

Week 4 · we said HOU by 3.5, total 51.6 · close HOU by 3.0, 48.5

Frozen Oct 4, 11:30 AM ET

34–30
Wrong winner
IND@WAS

Week 4 · we said IND by 2.3, total 51.5 · close IND by 4.0, 47

Frozen Oct 4, 5:14 AM ET

30–13
Right winner
PIT@CLE

Week 4 · we said CLE by 0.7, total 39.8 · close PIT by 2.5, 38

Frozen Oct 1, 7:52 PM ET

24–27
Right winner
PHI@CHI

Week 3 · we said PHI by 1.6, total 44.5 · close PHI by 3.5, 42.5

Frozen Sep 28, 7:52 PM ET

7–27
Wrong winner
LA@DEN

Week 3 · we said LA by 0.5, total 44.4 · close LA by 1.5, 44

Frozen Sep 27, 7:52 PM ET

26–30
Wrong winner
BAL@DAL

Week 3 · we said BAL by 4.0, total 53.0 · close BAL by 3.5, 53

Frozen Sep 27, 3:52 PM ET

34–31
Right winner
LV@NO

Week 3 · we said NO by 2.9, total 45.7 · close NO by 3.5, 43.5

Frozen Sep 27, 3:52 PM ET

35–27
Wrong winner
ARI@SF

Week 3 · we said SF by 11.8, total 47.7 · close SF by 7.5, 48

Frozen Sep 27, 3:52 PM ET

30–36
Right winner
MIN@TB

Week 3 · we said MIN by 4.9, total 42.8 · close MIN by 1.5, 42.5

Frozen Sep 27, 3:52 PM ET

23–16
Right winner
LAC@BUF

Week 3 · we said BUF by 8.7, total 47.5 · close BUF by 7.0, 50

Frozen Sep 27, 12:52 PM ET

16–24
Right winner
CAR@CLE

Week 3 · we said CLE by 0.7, total 41.7 · close CAR by 2.5, 42

Frozen Sep 27, 12:52 PM ET

18–21
Right winner
NYJ@DET

Week 3 · we said DET by 8.0, total 51.5 · close DET by 6.5, 48.5

Frozen Sep 27, 12:52 PM ET

24–31
Right winner
HOU@IND

Week 3 · we said IND by 0.1, total 51.1 · close HOU by 1.5, 42.5

Frozen Sep 27, 12:52 PM ET

17–19
Right winner
KC@MIA

Week 3 · we said KC by 6.5, total 45.6 · close KC by 10.0, 45.5

Frozen Sep 27, 12:52 PM ET

24–10
Right winner
TEN@NYG

Week 3 · we said NYG by 4.4, total 39.6 · close NYG by 2.5, 37.5

Frozen Sep 27, 12:52 PM ET

7–12
Right winner
CIN@PIT

Week 3 · we said CIN by 0.5, total 42.8 · close CIN by 3.0, 42.5

Frozen Sep 27, 12:52 PM ET

27–30
Wrong winner
SEA@WAS

Week 3 · we said SEA by 9.0, total 42.3 · close SEA by 8.5, 40.5

Frozen Sep 27, 12:52 PM ET

31–33
Wrong winner
NE@JAX

Week 3 · we said JAX by 0.9, total 42.5 · close JAX by 3.0, 46

Frozen Sep 27, 12:52 PM ET

6–35
Right winner

Legacy numbers (not in the headline)

Before the hourly snapshots, the site kept the first number any visitor happened to see, from an older version of the model, sometimes days before kickoff. They are shown here for the record but left out of every headline number above. 33% winners (5/15), 15.7 points off the margin, 12.6 off the total; closing line on the same games 13.2 off the margin.

ATL@GB

Week 3 · we said GB by 2.9, total 44.7 · close GB by 4.5, 43.5

First seen Sep 20, 12:57 PM ET

35–14
Wrong winner
NYG@LA

Week 2 · we said NYG by 2.3, total 43.1 · close LA by 6.5, 47.5

First seen Sep 19, 10:13 AM ET

6–28
Wrong winner
IND@KC

Week 2 · we said KC by 9.5, total 49.1 · close KC by 6.0, 46.5

First seen Sep 19, 10:13 AM ET

30–33
Right winner
WAS@DAL

Week 2 · we said DAL by 1.0, total 45.0 · close DAL by 3.5, 51.5

First seen Sep 19, 10:13 AM ET

20–37
Right winner
SEA@ARI

Week 2 · we said ARI by 3.4, total 36.2 · close SEA by 3.5, 40.5

First seen Sep 19, 10:13 AM ET

31–7
Wrong winner
MIA@SF

Week 2 · we said SF by 6.9, total 39.5 · close SF by 12.5, 44.5

First seen Sep 19, 10:13 AM ET

13–35
Right winner
JAX@DEN

Week 2 · we said JAX by 6.4, total 40.2 · close DEN by 2.5, 45.5

First seen Sep 19, 10:13 AM ET

13–20
Wrong winner
LV@LAC

Week 2 · we said LV by 3.3, total 39.7 · close LAC by 6.5, 43.5

First seen Sep 19, 10:13 AM ET

26–14
Right winner
CAR@ATL

Week 2 · we said ATL by 2.4, total 55.0 · close CAR by 2.5, 43.5

First seen Sep 19, 10:13 AM ET

34–3
Wrong winner
MIN@CHI

Week 2 · we said CHI by 5.8, total 65.4 · close CHI by 4.5, 46.5

First seen Sep 19, 10:13 AM ET

9–3
Wrong winner
PHI@TEN

Week 2 · we said PHI by 1.9, total 40.5 · close PHI by 7.0, 39.5

First seen Sep 19, 10:13 AM ET

24–20
Right winner
PIT@NE

Week 2 · we said PIT by 0.0, total 34.4 · close NE by 4.5, 41.5

First seen Sep 19, 10:13 AM ET

3–20
Tie
GB@NYJ

Week 2 · we said NYJ by 6.2, total 47.4 · close GB by 3.5, 44.5

First seen Sep 19, 10:13 AM ET

20–17
Wrong winner
CLE@TB

Week 2 · we said TB by 5.1, total 44.3 · close TB by 8.5, 41.5

First seen Sep 19, 10:13 AM ET

23–19
Wrong winner
NO@BAL

Week 2 · we said BAL by 10.2, total 58.0 · close BAL by 8.5, 45.5

First seen Sep 19, 10:13 AM ET

24–17
Wrong winner
CIN@HOU

Week 2 · we said HOU by 2.1, total 55.1 · close HOU by 3.0, 45.5

First seen Sep 19, 10:13 AM ET

20–6
Wrong winner

Reference table from earlier tracked games (not part of the frozen record above):

Total scoring guide

What the model total has meant in tracked games.

We saidCallRecord
38 or lessUnder 41Strongest8–0 (100%)
44 or lessUnder 4514–1 (93%)
45 to 54Over 456–1 (86%)
55+Skip5–4

The first two rows overlap. Every game at 38 or less is also in the 44-or-less row. When both apply, Under 41 is the stronger play.

2026 regular-season finals only. The walk-forward backtest, which recomputes every game with the current model, is on the methodology page and is labelled as a backtest there.