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 2026-09-13 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.
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
| Game | Date | Model home win | Market home win | Model total | Market total | Our projection | Status |
|---|---|---|---|---|---|---|---|
| Detroit Lions at Buffalo Bills | Thu Sep 17 | 56.6% | 60.4% | 54.4 | 52.5 | BUF 56.6%Over 52.5 | Not played yet |
| Carolina Panthers at Atlanta Falcons | Sun Sep 20 | 60.9% | 52.8% | 44.7 | 43.8 | ATL 60.9%Over 43.8 | Not played yet |
| Cincinnati Bengals at Houston Texans | Sun Sep 20 | 58.1% | 55.9% | 44.3 | 45.8 | HOU 58.1%Under 45.8 | Not played yet |
| Cleveland Browns at Tampa Bay Buccaneers | Sun Sep 20 | 63.0% | 73.7% | 41.5 | 40.5 | TB 63.0%Over 40.5 | Not played yet |
| Green Bay Packers at New York Jets | Sun Sep 20 | 25.3% | 31.9% | 45.7 | 42.5 | GB 74.7%Over 42.5 | Not played yet |
| Indianapolis Colts at Kansas City Chiefs | Sun Sep 20 | 54.0% | 70.2% | 44.4 | 47.5 | KC 54.0%Under 47.5 | Not played yet |
| Jacksonville Jaguars at Denver Broncos | Sun Sep 20 | 50.6% | 56.8% | 41.6 | 44.5 | Near evenUnder 44.5 | Not played yet |
| Las Vegas Raiders at Los Angeles Chargers | Sun Sep 20 | 66.5% | 77.4% | 40.9 | 42.5 | LAC 66.5%Under 42.5 | Not played yet |
| Miami Dolphins at San Francisco 49ers | Sun Sep 20 | 64.1% | 84.5% | 45.6 | 46.5 | SF 64.1%Under 46.5 | Not played yet |
| Minnesota Vikings at Chicago Bears | Sun Sep 20 | 46.1% | 59.4% | 41.1 | 45.5 | MIN 53.9%Under 45.5 | Not played yet |
| New Orleans Saints at Baltimore Ravens | Sun Sep 20 | 63.7% | 76.6% | 44.0 | 46.5 | BAL 63.7%Under 46.5 | Not played yet |
| Philadelphia Eagles at Tennessee Titans | Sun Sep 20 | 32.8% | 32.2% | 44.0 | 42.5 | PHI 67.2%Over 42.5 | Not played yet |
| Pittsburgh Steelers at New England Patriots | Sun Sep 20 | 67.5% | 64.6% | 40.9 | 43.5 | NE 67.5%Under 43.5 | Not played yet |
| Seattle Seahawks at Arizona Cardinals | Sun Sep 20 | 28.3% | 19.7% | 45.1 | 44.5 | SEA 71.7%Over 44.5 | Not played yet |
| Washington Commanders at Dallas Cowboys | Sun Sep 20 | 47.8% | 65.4% | 52.2 | 51.5 | WAS 52.2%Over 51.5 | Not played yet |
| New York Giants at Los Angeles Rams | Mon Sep 21 | 68.1% | 80.1% | 50.0 | 48.5 | LAR 68.1%Over 48.5 | Not played yet |
16 games. None of these games has been written into the record below yet. The weekly Tuesday update is what writes them down, and until it does these are the model's current numbers rather than logged projections. 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. In 1 of these games our win probability is inside two points of a coin flip, so it says near even rather than naming a team it does not actually separate. Our side is the other team from the market's favourite in 2 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, and a win probability inside two points of a coin flip gets no side at all, because a number that close has not separated the two teams.
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
| Measure | Our number | The market | Graded games |
|---|---|---|---|
| Moneyline, 2020-2024 out of sample | 0.2237 | 0.2099 | 1,404 |
| Moneyline, 2025 held-out season | 0.2206 | 0.2119 | 284 |
| Total points, 2020-2024 out of sample | 10.59 | 10.30 | 1,408 |
| Total points, 2025 held-out season | 10.59 | 10.43 | 285 |
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.
- No moneyline sides have been graded yet. 14 are logged and waiting for their games to finish. 2 published no side, because the number was inside two points of a coin flip or exactly on the quoted line.
- No Over or Under sides have been graded yet. 16 are logged and waiting for their games to finish.
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 version | State | Projections logged | Graded |
|---|---|---|---|
| Model v1 | Closed, still graded | 32 | 0 |
| Model v2 | Serves from 2026-09-15 | 0 | 0 |
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.
Every side we have published
| Game | Week | Version | Our projection | Status |
|---|---|---|---|---|
| NE at SEA | 2026 week 1 | Model v1 | SEA 69.7%Under 44.5 | Waiting on the result |
| SF at LAR | 2026 week 1 | Model v1 | LAR 75.0%Under 48.0 | Waiting on the result |
| ARI at LAC | 2026 week 1 | Model v1 | LAC 62.2%Under 47.5 | Waiting on the result |
| ATL at PIT | 2026 week 1 | Model v1 | ATL 52.8%Over 42.0 | Waiting on the result |
| BAL at IND | 2026 week 1 | Model v1 | BAL 67.2%Under 48.0 | Waiting on the result |
| BUF at HOU | 2026 week 1 | Model v1 | BUF 57.4%Under 44.5 | Waiting on the result |
| CHI at CAR | 2026 week 1 | Model v1 | CHI 61.5%Under 47.0 | Waiting on the result |
| CLE at JAX | 2026 week 1 | Model v1 | JAX 70.8%Over 40.5 | Waiting on the result |
| DAL at NYG | 2026 week 1 | Model v1 | Near evenUnder 48.0 | Waiting on the result |
| GB at MIN | 2026 week 1 | Model v1 | MIN 54.9%Under 46.5 | Waiting on the result |
| MIA at LV | 2026 week 1 | Model v1 | MIA 67.8%Over 40.5 | Waiting on the result |
| NO at DET | 2026 week 1 | Model v1 | Near evenUnder 50.0 | Waiting on the result |
| NYJ at TEN | 2026 week 1 | Model v1 | TEN 59.5%Over 39.5 | Waiting on the result |
| TB at CIN | 2026 week 1 | Model v1 | CIN 57.7%Under 50.5 | Waiting on the result |
| WAS at PHI | 2026 week 1 | Model v1 | PHI 67.9%Under 44.5 | Waiting on the result |
| DEN at KC | 2026 week 1 | Model v1 | DEN 53.6%Under 43.5 | Waiting 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
- Projections are written down before kickoff and cannot be edited afterwards. Model v2, stamped 2026-09-13.
- The side is derived from the two published numbers and has no other input. It is the team above a coin flip, or Over or Under against the quoted line, and a win probability within two points of a coin flip publishes no side.
- The market number is 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.
- We and the market are always scored on exactly the same games. A game missing either number is counted on neither side rather than filled in.
- A tie voids the moneyline row rather than counting as a loss. The total for that same game still grades. A final that lands exactly on the quoted total is a push.
- Both halves of every average are published separately, so the two estimates behind each number can be read individually rather than taken on trust.
- Nothing on this page is betting advice. Nebula Insights publishes no picks, no selections and no recommended wagers.
Next steps
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 does a game say near even instead of naming a team?
Because our win probability for it is inside two points of a coin flip. A number that close has not separated the two teams, so naming one would be inventing a side the number does not support.
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.