This page publishes our model's number for every upcoming NFL game beside the market's own number for the same game, and it names the side those two numbers imply. That side is arithmetic, not a selection, and it is not a pick. On the games graded so far the model trails the market on both the moneyline and the total, and this page publishes that gap.

Model v2, stamped 2026-10-27 and rebuilt every Tuesday. For the market's full board see the NFL odds board, the per book prices on the price grid, and the full ledger on the track record.

+0.0138how far behind the market we areBrier score gap on the moneyline, 1,404 graded games. Lower is better, so a positive number is us trailing.

Where this model stands

Our NFL model is measured against the market on every graded game. It currently trails the market on both moneyline and total points, and we publish the gap.

That sentence is the whole standing disclosure and it is not softened anywhere on this page. The size of the gap is set out further down, measured on graded games with the count printed beside it.

This week's games

GameDateModel home winMarket home winModel totalMarket totalOur projectionStatus
Carolina Panthers at Green Bay PackersThu Oct 2964.5%63.8%45.548.0GB 64.5%Under 48.0Waiting on the result
Arizona Cardinals at Dallas CowboysSun Nov 0164.0%71.2%51.354.5DAL 64.0%Under 54.5Waiting on the result
Atlanta Falcons at Tampa Bay BuccaneersSun Nov 0159.6%54.7%45.846.0TB 59.6%Under 46.0Waiting on the result
Baltimore Ravens at Buffalo BillsSun Nov 0161.4%62.3%52.953.5BUF 61.4%Under 53.5Waiting on the result
Cleveland Browns at Pittsburgh SteelersSun Nov 0157.9%62.9%40.339.5PIT 57.9%Over 39.5Waiting on the result
Indianapolis Colts at Jacksonville JaguarsSun Nov 0167.7%76.6%47.246.5JAX 67.7%Over 46.5Waiting on the result
Kansas City Chiefs at Denver BroncosSun Nov 0147.6%47.6%39.341.0KC 52.4%Under 41.0Waiting on the result
Los Angeles Chargers at Los Angeles RamsSun Nov 0171.7%72.0%44.544.5LAR 71.7%Under 44.5Waiting on the result
Las Vegas Raiders at New York JetsSun Nov 0153.2%50.0%44.545.5NYJ 53.2%Under 45.5Waiting on the result
Minnesota Vikings at Detroit LionsSun Nov 0155.7%61.3%43.446.0DET 55.7%Under 46.0Waiting on the result
New England Patriots at Miami DolphinsSun Nov 0133.9%24.5%42.844.5NE 66.1%Under 44.5Waiting on the result
Philadelphia Eagles at Washington CommandersSun Nov 0151.4%64.7%45.040.5WAS 51.4%Over 40.5Waiting on the result
Tennessee Titans at Cincinnati BengalsSun Nov 0177.9%81.6%47.246.5CIN 77.9%Over 46.5Waiting on the result
Chicago Bears at Seattle SeahawksMon Nov 0269.1%60.8%45.246.5SEA 69.1%Under 46.5Waiting on the result

14 games. The side is read off the two numbers to its left and nothing else: the team our win probability puts above a coin flip, and Over or Under depending on which way our projected points fall against the quoted line. Our side is the other team from the market's favourite in 0 of them. That is worth knowing and it is not worth acting on, for the reason set out below. "Model" is this week's published number for the home team winning and for the two teams' combined points. "Market" is the consensus of each book's latest archived quote before kickoff, with the bookmaker margin removed. It is not a closing line.

What the model's side is, and what it is not

The side is arithmetic. Whichever team our win probability puts above a coin flip is the side, and whichever way our projected points fall against the quoted line is Over or Under. There is no judgement in it, no game we single out and no game we leave alone. Every game gets a side, including the close ones, because a number we published is a number we are willing to be graded on.

What it is not is a recommendation. It is tempting to read our side disagreeing with the market as something to act on. On our own measured record it is not. Over 1,404 graded games our moneyline probability scores 0.2237 against the market's 0.2099 on the same games, and lower is better. Where the two disagree, the market has been right more often than we have. We print the side because doing the subtraction in your head is our job and not yours, and we print the record beside it for exactly the same reason.

How far behind the market we are

MeasureOur numberThe marketGraded games
Moneyline, 2020-2024 out of sample0.22370.20991,404
Moneyline, 2025 held-out season0.22060.2119284
Total points, 2020-2024 out of sample10.5910.301,408
Total points, 2025 held-out season10.5910.43285

Moneyline is a Brier score and total points is an average error in points. Lower is better in every row, so the market's is the better number in every row. On the two 2025 rows the gap is small enough that a single season cannot measure it, which is a statement about how little 285 games can settle and not a claim that we have caught up.

The record so far

Every projection here was written down before kickoff and cannot be edited afterwards, so this fills in on its own as results land, losses included.

How the side we named has done, across every week we have published.

Which version published which week. Week 1 of 2026 was projected by model v1. Model v2 serves from 2026-09-15 and is what the games above are built on. Version 1 receives no new games ever again, and it is still graded, because the games it projected are real and they are owed their results. The record is therefore split by version and a pooled figure can never hide inside a version change.

Model versionStateProjections loggedGraded
Model v1Closed, still graded3232
Model v2Serving178149

Counts are across both markets, the moneyline and the total. A projection counts as graded only when both our number and the market's number exist for that game, so a game missing either one counts on neither side.

MarketGraded gamesOur errorMarket errorUs minus market
NFL Moneyline900.241860.23959+0.00227
NFL total points9111.0238510.98077+0.04308

Lower is better in both of the middle values, so a positive figure at the end means we trailed the market over these games. We and the market are scored on exactly the same games.

Every side we have published

GameWeekVersionOur projectionStatus
NE at SEA2026 week 1Model v1SEA 69.7%Under 44.5Side right
SF at LAR2026 week 1Model v1LAR 75.0%Under 48.0Side wrongSide right
ARI at LAC2026 week 1Model v1LAC 62.2%Under 47.5Side wrongSide right
ATL at PIT2026 week 1Model v1ATL 52.8%Over 42.0Side wrong
BAL at IND2026 week 1Model v1BAL 67.2%Under 48.0Side rightSide wrong
BUF at HOU2026 week 1Model v1BUF 57.4%Under 44.5Side rightSide wrong
CHI at CAR2026 week 1Model v1CHI 61.5%Under 47.0Side rightSide wrong
CLE at JAX2026 week 1Model v1JAX 70.8%Over 40.5Side right
DAL at NYG2026 week 1Model v1NYG 50.2%Under 48.0Side rightPush
GB at MIN2026 week 1Model v1MIN 54.9%Under 46.5Side rightSide wrong
MIA at LV2026 week 1Model v1MIA 67.8%Over 40.5Side wrong
NO at DET2026 week 1Model v1NO 51.7%Under 50.0Side wrong
NYJ at TEN2026 week 1Model v1TEN 59.5%Over 39.5Side wrong
TB at CIN2026 week 1Model v1CIN 57.7%Under 50.5Side rightSide wrong
WAS at PHI2026 week 1Model v1PHI 67.9%Under 44.5Side rightSide wrong
DEN at KC2026 week 1Model v1DEN 53.6%Under 43.5Side wrongSide right
DET at BUF2026 week 2Model v2BUF 62.0%Over 53.5Side right
CAR at ATL2026 week 2Model v2ATL 58.9%Over 43.5Side wrong
CIN at HOU2026 week 2Model v2HOU 56.3%Over 46.5Side wrong
CLE at TB2026 week 2Model v2TB 67.6%Over 41.5Side wrongSide right
GB at NYJ2026 week 2Model v2GB 72.5%Over 44.5Side rightSide wrong
IND at KC2026 week 2Model v2KC 59.1%Under 46.5Side rightSide wrong
JAX at DEN2026 week 2Model v2JAX 53.3%Under 45.5Side wrongSide right
LV at LAC2026 week 2Model v2LAC 63.1%Under 43.5Side wrongSide right
MIA at SF2026 week 2Model v2SF 72.0%Under 45.5Side rightSide wrong
MIN at CHI2026 week 2Model v2CHI 54.2%Under 48.5Side wrongSide right
NO at BAL2026 week 2Model v2BAL 71.2%Under 47.0Side wrongSide right
PHI at TEN2026 week 2Model v2PHI 70.9%Over 39.5Side right
PIT at NE2026 week 2Model v2NE 66.2%Under 41.5Side right
SEA at ARI2026 week 2Model v2SEA 67.6%Over 41.0Side rightSide wrong
WAS at DAL2026 week 2Model v2DAL 50.8%Over 50.5Side right
NYG at LAR2026 week 2Model v2LAR 62.0%Over 48.5Side rightSide wrong
ATL at GB2026 week 3Model v2GB 72.0%Under 44.5Side wrong
ARI at SF2026 week 3Model v2SF 71.0%Under 48.0Side rightSide wrong
BAL at DAL2026 week 3Model v2BAL 61.6%Over 52.5Side right
CAR at CLE2026 week 3Model v2CAR 50.7%Over 42.0Side wrong
CIN at PIT2026 week 3Model v2CIN 55.5%Over 42.5Side wrongSide right
HOU at IND2026 week 3Model v2HOU 55.0%Over 43.5Side wrong
KC at MIA2026 week 3Model v2KC 66.9%Under 46.0Side right
LAC at BUF2026 week 3Model v2BUF 73.2%Under 50.5Side right
LAR at DEN2026 week 3Model v2LAR 54.9%Under 45.5Side wrong
LV at NO2026 week 3Model v2NO 68.5%Under 43.5Side wrong
MIN at TB2026 week 3Model v2MIN 56.0%Under 42.5Side right
NE at JAX2026 week 3Model v2JAX 59.9%Under 45.5Side right
NYJ at DET2026 week 3Model v2DET 78.7%Over 48.0Side right
SEA at WAS2026 week 3Model v2SEA 67.5%Over 40.0Side wrongSide right
TEN at NYG2026 week 3Model v2NYG 62.4%Over 40.5Side rightSide wrong
PHI at CHI2026 week 3Model v2CHI 50.6%Over 44.0Side rightSide wrong
TB at DAL2026 week 5Model v2DAL 53.2%Over 47.5Side wrong
BAL at ATL2026 week 5Model v2BAL 62.5%Over 44.5Side right
CHI at GB2026 week 5Model v2CHI 54.6%Over 45.0Side wrong
CIN at MIA2026 week 5Model v2CIN 65.3%Over 42.5Side right
CLE at NYJ2026 week 5Model v2CLE 54.3%Over 40.0Side wrong
DEN at LAC2026 week 5Model v2DEN 56.3%Under 42.0Side right
DET at ARI2026 week 5Model v2DET 64.3%Under 54.5Side rightSide wrong
HOU at TEN2026 week 5Model v2HOU 61.5%Over 39.5Side rightSide wrong
IND at PIT2026 week 5Model v2IND 51.4%Over 44.5Side wrongSide right
LV at NE2026 week 5Model v2NE 64.4%Under 45.0Side rightSide wrong
MIN at NO2026 week 5Model v2MIN 59.7%Under 42.0Side right
NYG at WAS2026 week 5Model v2NYG 53.6%Over 43.5Void, tieSide right
PHI at JAX2026 week 5Model v2JAX 66.5%Under 42.5Side right
SF at SEA2026 week 5Model v2SEA 58.8%Under 47.0Side wrong
BUF at LAR2026 week 5Model v2LAR 53.8%Under 54.5Side wrong
SEA at DEN2026 week 6Model v2SEA 54.8%Over 40.5Side wrong
ARI at LAR2026 week 6Model v2LAR 76.7%Under 52.5Side wrongSide right
BAL at CLE2026 week 6Model v2BAL 67.7%Over 41.5Side wrong
BUF at LV2026 week 6Model v2BUF 74.0%Under 53.5Side rightSide wrong
CAR at PHI2026 week 6Model v2PHI 55.1%Over 41.5Side wrong
CHI at ATL2026 week 6Model v2CHI 51.2%Under 49.2Side rightSide wrong
DAL at GB2026 week 6Model v2GB 59.3%Under 53.0Side right
HOU at JAX2026 week 6Model v2JAX 64.6%Under 42.5Side wrong
LAC at KC2026 week 6Model v2KC 73.2%Under 42.0Side right
NO at NYG2026 week 6Model v2NYG 59.1%Under 45.5Side wrong
NYJ at NE2026 week 6Model v2NE 74.3%Under 43.5Side rightSide wrong
PIT at TB2026 week 6Model v2TB 51.4%Over 40.5Side wrongSide right
TEN at IND2026 week 6Model v2IND 69.5%Over 44.0Side wrongSide right
WAS at SF2026 week 6Model v2SF 72.5%Under 50.5Side right
NE at CHI2026 week 7Model v2CHI 52.5%Under 50.5Side rightSide wrong
CIN at BAL2026 week 7Model v2BAL 59.2%Under 51.0Side wrongSide right
CLE at TEN2026 week 7Model v2CLE 59.0%Under 38.5Side rightSide wrong
DEN at ARI2026 week 7Model v2DEN 63.4%Under 43.5Side rightSide wrong
GB at DET2026 week 7Model v2DET 61.7%Under 53.5Side right
IND at MIN2026 week 7Model v2MIN 62.3%Over 41.5Side rightSide wrong
KC at SEA2026 week 7Model v2SEA 55.8%Over 42.5Side rightSide wrong
LAR at LV2026 week 7Model v2LAR 68.3%Over 47.5Side right
MIA at NYJ2026 week 7Model v2NYJ 52.1%Over 39.0Side wrongSide right
NYG at HOU2026 week 7Model v2HOU 64.8%Over 43.0Side wrongSide right
PIT at NO2026 week 7Model v2PIT 58.2%Under 44.5Side right
SF at ATL2026 week 7Model v2SF 67.0%Under 50.5Side wrongSide right
TB at CAR2026 week 7Model v2CAR 64.2%Over 44.5Side wrongSide right
DAL at PHI2026 week 7Model v2PHI 55.9%Over 44.0Side wrongSide right
CAR at GB2026 week 8Model v2GB 64.5%Under 48.0Waiting on the result
ARI at DAL2026 week 8Model v2DAL 64.0%Under 54.5Waiting on the result
ATL at TB2026 week 8Model v2TB 59.6%Under 46.0Waiting on the result
BAL at BUF2026 week 8Model v2BUF 61.4%Under 53.5Waiting on the result
CLE at PIT2026 week 8Model v2PIT 57.9%Over 39.5Waiting on the result
IND at JAX2026 week 8Model v2JAX 67.7%Over 46.5Waiting on the result
KC at DEN2026 week 8Model v2KC 52.4%Under 41.0Waiting on the result
LAC at LAR2026 week 8Model v2LAR 71.7%Under 44.5Waiting on the result
LV at NYJ2026 week 8Model v2NYJ 53.2%Under 45.5Waiting on the result
MIN at DET2026 week 8Model v2DET 55.7%Under 46.0Waiting on the result
NE at MIA2026 week 8Model v2NE 66.1%Under 44.5Waiting on the result
PHI at WAS2026 week 8Model v2WAS 51.4%Over 40.5Waiting on the result
TEN at CIN2026 week 8Model v2CIN 77.9%Over 46.5Waiting on the result
CHI at SEA2026 week 8Model v2SEA 69.1%Under 46.5Waiting on the result

Every side we have published, oldest first, with the model version that produced it. Nothing is removed from this list once a result lands.

What the model is

Each number is the average of two independent estimates of the same game. The first reads each team's recent efficiency, its prior-season strength, rest, travel, kickoff slot, surface and roof, and the announced starting quarterback. The second simulates the game's scoring events directly and plays it twenty thousand times. Averaging two independent estimates is a standard way to reduce error. It does not add information that neither of them had, and neither of them reads the betting market, which is what keeps the comparison on this page honest.

An improved model is a stated goal, not a promise. The version label above is the real one, and when it changes this page will say what changed and show both sets of numbers.

How these numbers are made and checked

Frequently asked questions

Is the model's side a pick?

No. It is arithmetic done for you: the team our published win probability puts above a coin flip, and Over or Under depending on which way our projected points fall against the quoted line. We publish no picks, no selections and no recommended wagers, and our record against the market is printed beside every side.

Your side and the market's favourite disagree. What does that mean?

On our measured record it means we are more likely to be wrong than the market is. Over 1,404 graded games our moneyline probability scored 0.2237 against the market's 0.2099 on the same games, and lower is better.

Why publish a model that trails the market?

Because the number is still informative and the honest thing is to show it with its record attached. Every projection is logged before kickoff and graded afterwards, losses included, so the claim is checkable rather than asserted.

What is the market number exactly?

The consensus of each bookmaker's latest archived quote strictly before kickoff, with the bookmaker margin removed. It is not a closing line and we never describe it as one.

Related: NFL odds board · NFL price grid · Public track record

This guide explains how a betting market works and how the arithmetic is done. It is information, not betting advice: Nebula Insights publishes no picks, no selections and no recommended wagers. Sportsbook rules vary by book and jurisdiction, so always confirm the house rules that apply to your account. You must be of legal gambling age in your jurisdiction.