Model accuracy & track record

Every NFL model here, graded against real results.

How these are graded

Weekly projections: team environment x volume shares x efficiency x xTD allocation (DraftKings), graded per player week against the box score. Draft tiers: frozen preseason consensus, clustered by position, refit leave one season out and scored on the real season. Game model: QB adjusted Elo, graded against the market with the vig removed. Numbers refresh as results land.

This season, locked before kickoff

2026 live record
Live record

Picks lock at kickoff and grade from the final score. Nothing is added or removed after kickoff.

12-4
engine, 1 week
75.0%
straight up
12-4
closing line, same games

Weekly projections

2025 holdout, every player

Every weekly projection, graded against the box score.

Weekly projections

r is the correlation between projected and actual DraftKings points on the 2025 holdout. Form is a recent form baseline, a higher r beats it. The rank bands below are measured on the 2025 holdout, a season the model was not fitted on. Live weeks grade as they finish. The headline stays on the 2025 holdout until the live sample is big enough.

20.8
avg points, our top nine
6.6
avg points, the field
QB
0.55
form 0.47
RB
0.70
form 0.68
WR
0.64
form 0.63
TE
0.64
form 0.62
DST
0.30
form 0.07
K
0.17
form 0.11

r to actual · form = recent form baseline · 2025 holdout

2026 live · 1 slate graded
20.2
avg points, our top nine
7.4
avg points, the field

// What a RB rank here has actually been worth

Where players we ranked in each band really finished, across the 2025 season. The bar is the middle half of outcomes, the notch is the median. Wide bars are the honest part: this is a weekly game and the order is a lean, not a promise.

RB1-RB3
RB2.25 to RB11
RB4-RB6
RB8 to RB18.5
RB7-RB12
RB7 to RB23
RB13-RB24
RB11 to RB29.25
RB25-RB48
RB25 to RB48

Measured on the 2025 holdout, the season nothing was fitted on. Sample sizes run 54 to 432 player weeks per band.

// What a WR rank here has actually been worth

Where players we ranked in each band really finished, across the 2025 season. The bar is the middle half of outcomes, the notch is the median. Wide bars are the honest part: this is a weekly game and the order is a lean, not a promise.

WR1-WR3
WR3 to WR18
WR4-WR6
WR6.5 to WR28.75
WR7-WR12
WR9.75 to WR34.25
WR13-WR24
WR12 to WR42.25
WR25-WR48
WR25.75 to WR59

Measured on the 2025 holdout, the season nothing was fitted on. Sample sizes run 54 to 432 player weeks per band.

// What a QB rank here has actually been worth

Where players we ranked in each band really finished, across the 2025 season. The bar is the middle half of outcomes, the notch is the median. Wide bars are the honest part: this is a weekly game and the order is a lean, not a promise.

QB1-QB3
QB4 to QB12.75
QB4-QB6
QB4 to QB14
QB7-QB12
QB5 to QB15.25
QB13-QB24
QB11 to QB22.25

Measured on the 2025 holdout, the season nothing was fitted on. Sample sizes run 54 to 192 player weeks per band.

// What a TE rank here has actually been worth

Where players we ranked in each band really finished, across the 2025 season. The bar is the middle half of outcomes, the notch is the median. Wide bars are the honest part: this is a weekly game and the order is a lean, not a promise.

TE1-TE3
TE2 to TE12.5
TE4-TE6
TE6.25 to TE22.75
TE7-TE12
TE8 to TE26
TE13-TE24
TE10 to TE33
TE25-TE48
TE25 to TE52

Measured on the 2025 holdout, the season nothing was fitted on. Sample sizes run 54 to 432 player weeks per band.

// What a DST rank here has actually been worth

Where players we ranked in each band really finished, across the 2025 season. The bar is the middle half of outcomes, the notch is the median. Wide bars are the honest part: this is a weekly game and the order is a lean, not a promise.

DST1-DST3
DST4 to DST10
DST4-DST6
DST4 to DST14
DST7-DST12
DST6 to DST16
DST13-DST24
DST10.75 to DST21.25

Measured on the 2025 holdout, the season nothing was fitted on. Sample sizes run 54 to 108 player weeks per band.

// How this board has actually scored

Rank correlation with what players really scored, on the drafted universe, for every season we can grade. Two yardsticks: last year’s points, which is the naive answer, and the market’s average draft position, which is the hard one.

SeasonPlayersUsLast yearMarketFirst 50 picks
20222220.6390.6400.6520.267 v 0.334
20233270.7030.6550.7620.317 v 0.224
20244690.7570.7310.7590.204 v 0.342
20254680.7680.7630.7600.275 v 0.506

Read that honestly. We beat last year’s points in 3/4 seasons, which is the bar. We beat the market in 1/4 — so this is market competitive, not market beating. And in the first fifty picks the market is clearly ahead. The pooled number is carried by the deep pool, where the only question is whether a player starts at all.

  • Rookies are absent entirely: no prior history to project from, so this scores veterans only.
  • ADP prices holdouts, camp battles, suspensions and trades that this model cannot see.

Draft tier track record

2019-2024

How each draft tier actually finished, full PPR.

Draft tiers

Graded leave one season out, so a season’s tiers never see that season’s results. Median finish is the middle actual positional finish. League winner is an elite year, top 3 at QB, TE, K and DST, top 6 at RB and WR. Bust is a finish outside the startable range. A tier one rank wide has no tier record, one player held it. QB and TE top tiers are small samples. Kicker and defense are graded but not shown.

Running back

TierDraft costMedian finishLeague-winnerBustSample
T1RB1-6RB1331%19%32
T2RB5-15RB1128%12%57
T3RB15-24RB2312%28%25
T4RB16-32RB265%35%40
T5RB19-41RB345%47%43
T6RB24-50RB432%58%57
T7RB33-62RB452%70%57
T8RB42-68RB770%85%59

Wide receiver

TierDraft costMedian finishLeague-winnerBustSample
T1WR1-7WR945%16%31
T2WR5-19WR1427%18%33
T3WR8-22WR209%18%55
T4WR10-38WR383%41%74
T5WR24-45WR376%38%52
T6WR39-57WR602%64%58
T7WR43-60WR523%64%39
T8WR55-65WR770%84%38

Quarterback

TierDraft costMedian finishLeague-winnerBustSample
T1QB1-3QB720%10%10
T2QB2-4QB443%0%7
T3QB3-8QB937%21%19
T4QB5-13QB1611%52%27
T5QB9-18QB146%39%31
T6QB14-24QB223%69%32
T7QB19-32QB260%71%31
T8QB25-34QB270%82%22

Tight end

TierDraft costMedian finishLeague-winnerBustSample
T1TE1one player deep, no tier record6
T2TE2-5TE636%36%14
T3TE4-8TE117%43%14
T4TE5-11TE1315%35%20
T5TE9-15TE135%45%20
T6TE12-26TE220%74%31
T7TE14-32TE235%67%39
T8TE19-34TE290%83%30

Game & win model

2019-2025 holdout

Powers Winners, Survivor and Pick 6. Graded straight up on 1,865 games.

Game model

Brier scores the win probability, lower is better. The market moneyline is the ceiling. The blend matches it on priced weeks and the model alone covers unpriced weeks.

Straight-up accuracy
66.5%
Model-only accuracy
64.5%
covers unpriced weeks
Brier vs market
0.210
market 0.210