Model Score: how the number is built
Model Score is one number, 0 to 100, for every college player: how good is he, and how much should an NFL team want him, based on everything his college career shows. The median is about 70. A 95 is rare.
How a season is graded
Each season, his stats are ranked against every player at his position that year, so a guard is compared to guards and 2025 to 2025. Then the season is adjusted three ways:
- Competition. His conference (an SEC season counts for more than a MAC season) and the actual defenses or offenses he faced, adjusted for who those teams played.
- Age. A big season as a freshman counts for more than the same season as a fifth-year senior. Doing it young is what the NFL pays for.
- Sample size. A three-game hot streak is pulled toward an average season. For linemen it is pass-block snaps, not games, that decide how much a season counts.
How the career score is built
The career score mixes his seasons (this one, his best one, and his average) with the things scouts weigh that a box score cannot see: honors (All-America and all-conference teams, voted on by people who watched the film), recruiting pedigree, size for the position, how early he broke out, and for defensive backs, how good the pass defense he played in was. Each position gets its own mix:
| Position | Stats | Honors | Pedigree | Size | Breakout | Pass defense |
|---|---|---|---|---|---|---|
| QB | 65% | - | 20% | 10% | 5% | - |
| RB | 80% | 10% | - | 5% | 5% | - |
| WR | 50% | 20% | 20% | 5% | 5% | - |
| TE | 45% | 20% | 10% | 20% | 5% | - |
| OT | 35% | 30% | 20% | 10% | 5% | - |
| Interior OL | 35% | 30% | 20% | 10% | 5% | - |
| EDGE | 60% | 20% | - | 15% | 5% | - |
| Interior DL | 35% | 20% | 20% | 20% | 5% | - |
| LB | 55% | - | 20% | 20% | 5% | - |
| CB | 30% | 20% | 20% | 15% | 5% | 10% |
| S | 50% | 20% | - | 5% | 5% | 10% |
Every weight was chosen the same way: we tested it against where players actually got drafted from 2016 on, and kept it only if it made the score better at that in both halves of the history, not just overall. A piece that did not help stayed out, which is why quarterbacks and linebackers carry no honors weight.
The Projection column
The big board turns the score into a draft round. Each round has a score that its picks typically had (a first-rounder about 88, a top-10 pick about 93). The scouts' consensus rank sets the floor: we never project a player lower than the round his rank usually lands in at this point of the season. Our score can lift him up to two labels above it. A player the scouts have outside the draft needs a score of 84 or better before we project him in.
Why it moves
It is recomputed every week. A senior having a worse year than his junior year goes down, and should.
Where it is honest about being weak
There is no free data on who a cornerback was covering or who got to the quarterback, so the best cover men and pass rushers are read through their honors, their team's pass defense and their pedigree rather than their own snaps. Interior offensive line is still the position where the score and the draft agree least. Combine numbers are not in it yet.
We publish all eleven positions anyway. A number that only appears where it looks good is not a number you can trust.
Coverage
18,899 college players have a Model Score across eleven positions. 10,469 of them have a profile page - those are the players with two or more scored seasons. A player with one season has a score that leans mostly on his recruiting profile, and a page built on that is worse than no page.
Where to see it
- Big Board - a sortable Model column next to the consensus rank
- Prospect Analytics - sorted by Model Score
- College Team HQ - every roster, plus Position Rooms ranked by Model Score
- Any college player profile page