News4h ago
Scouts already know where Arch Manning will land in 2027 NFL Draft
The Big Lead
2018–2022 backtest · graded against real NFL careers · the receipts →
Next draftApril 22-24, 2027 · Green Bay (TBC)
The best draft board public data can build.
Every prospect, graded on the only question that matters: how good an NFL career do they actually go on to have? Backtested out of sample across 2018–2022, Draftanomics's board predicts real career value at 0.52 — ahead of the analyst consensus (0.37) and a step shy of NFL war rooms (0.60), who grade with the medicals, interviews, and private workouts no public site ever sees.We publish the calibration, the misses, and both the k-fold and the leave-one-year-out numbers, so you can check all of it.
That's the rank correlation between each board's order and players' eventual Career Score — our open-data career-value index, built from snap participation, durability, and what the market actually paid them on a second contract — where 0 is a coin flip and 1 is perfect foresight. Scored only on classes the model never trained on.
The board, right nowAll 2027 →
- 1
Jeremiah Smith · WR, Ohio StateJeremiah Smith already plays like the finished product at receiver — a 6-foot-3, 214-pound frame that still turns on the jets vertically, with cushion that reportedly sends cornerbacks into panic mode at four yards off the ball. The model puts him at No. 1 overall for 2027, exactly where the consensus board of 22 outlets has him, too.
- 2
Leonard Moore · CB, Notre DameLeonard Moore plays corner like a matchup problem — long speed to run with verticals, quick feet to click and close, and a habit of baiting quarterbacks into throws he has no business getting to. The model slots him at No. 2 on the 2027 board, just ahead of the room's consensus at No. 4, and for a projected elite-tier corner, model and room are pointed the same direction.
- 3
Trevor Goosby · OT, TexasTrevor Goosby wins with length and violence in his hands, a blend that lets him anchor against power and still toss rushers off their spot once he's latched on. The model has him third overall, well clear of a No. 9 consensus, and both sides agree on the same conclusion: this is a blue-chip tackle after just one year starting at Texas.
- 4
Colin Simmons · EDGE, TexasColin Simmons wins before the tackle can even set his hands — the first step gets him level immediately, and the bend that follows grades as elite in its own right. The model board has him at No. 4, two spots off a consensus No. 2, and here the 22 boards are reading from the same script. Texas already has him at 21 career sacks in two seasons, and the model's own tier call on him is elite.
- 5
Jordan Seaton · OT, LSUJordan Seaton looks like a left tackle prospect built to anchor an offensive line for a decade, the rare blend of length and lateral quickness scouts don't stop talking about. The model has him at No. 5 on the 2027 board, tight with a consensus rank of 7 across 22 boards — this is one where the algorithm and the room are reading the same guy.
The wire
Latest on the board
Portal moves, consensus-board movement, new boards and mocks, fresh scouting reports, and draft-media coverage for the 2027 class.
- New board19h ago
New board added: Andy NFL — 57 prospects ranked
Andy NFL - Report3d ago
Ryan Williams wins in short-area space, turning burst out of his stance into shake after the catch that Best Available's film notes call legitimate YAC juice.
Draftanomics - Mover▼1493d ago
Down 149 spots on the consensus board since the last freeze (No. 24 → No. 173) — our board still has him No. 9
Frozen ledger - News5h ago
GENERATIONAL ATHLETE: South Carolina’s Nick Harbour DESTROYS Defenses With Shocking NFL Traits
Locked On NFL Draft (YouTube) - New board11d ago
New mock added: PFN mock (Weil) — 28 picks
PFN mock (Weil)
The lead · August 3
Camp Opens, the Board Shakes Out, and the Model Digs In on Adam Trick
A six-and-a-half-day window produced the board's ugliest slide of the summer and its widest model-versus-room gap yet.
Read the piece →Track record
The receipts
Full backtest: 11 draft classes, 2015–2025 — every year graded by a model trained without it.
The editorial
What we're writing
- 2026-08-03·4 min readCamp Opens, the Board Shakes Out, and the Model Digs In on Adam Trick
A six-and-a-half-day window produced the board's ugliest slide of the summer and its widest model-versus-room gap yet.
- 2026-07-28·4 min readJordan Ross Jumps 20 Spots While the Model Won't Move an Inch
The board fell in love with an LSU edge rusher this week, but Draftanomics's numbers still have him buried outside the top 160.
- 2026-06-08·4 min readBetter than the consensus, a step shy of the league
How the board is graded against real NFL careers, where it beats the analyst consensus, and where it still trails NFL war rooms. (Written June 2026, under our previous career-value ruler.)
The class at a glance
Model run just now2027 draft class
The model's elite and bustcalls are its reliable ones — the middle tiers are closer to coin flips, so they're shown muted.
Ranked prospects
188
on the consensus board
Elite bets
5
Better-than-even shot at a star career
Likely starters+
147
At least a 60% chance he becomes an NFL starter or better
Real bust risk
19
Bust probability 30% or higher — top 100 on the board, same number the position pages quote
Scarcest premium
G
2 starter+ grades
Position-group tier mix · the model's top 200
elitestarterrolebust
QB
21prospects
RB
24prospects
WR
43prospects3 elite
TE
13prospects
OT
9prospects
G
6prospects
EDGE
14prospects1 elite
DL
21prospects
LB
25prospects
CB
14prospects1 elite
S
9prospects
The 2027 class is deepest at WR (38 starter-grade or better) and thinnest at G (2). Teams with a top-half pick and a G need should consider reaching or trading up.
Full board →The Scouting Slate · game of the week
Full slate →San José State at USC · Saturday, Aug 29
USC's rebuilt front seven gets its first live test, and Kameryn Fountain, our No. 19 overall, is the reason to tune in—an interior disruptor who should feast on tape all night. San José State's Jordan Pollard, our No. 65 linebacker, faces the harder job: proving he can diagnose and finish against a roster overflowing with future NFL talent.
The next class
2027 NFL Draft
188 prospects with analyst coverageOpen the board and build your own read on the class — tag your sleepers, rank your guys, and see exactly where you break from the model. When you disagree, put two prospects side by side or stack your board against Draftanomics's on your big board.
Honest accuracy(how)catches 79% of eventual busts before draft day
Highest elite odds right now
Watchouts — high ceiling, highest bust risk in the class
What we ship that no other draft site does
Three honest moves the consensus draft sites don't make.
Where we're wrong
Named failure modes
Every model has blind spots. Ours can barely tell which interior linemen will bust — those calls are no better than a coin flip. We publish the failures — the alternative is selling overconfidence.
Read the failure modes →
Risk × reward
The boom-bust quadrant
Every prospect plotted by bust probability against elite ceiling. Sleepers in the top-left, boom-busts top-right, fades bottom-right. The picture the consensus board hides.
Open the quadrant →
The room
Scout-synthesis prose
Our models read every public scouting report and analyst board on a prospect, then write the synthesized take — with a citation behind every film claim and a validator that kills the sentence if a number doesn't trace. More than 400 prospects covered.
See an example dossier →
The Tuesday tab
Get the model dissents in your inbox.
One email per week during the cycle (combine through May). Where the model breaks from consensus + the receipt to back it up. Monthly off-cycle. Free, no spam, easy unsubscribe.
How the model has done
These years are the backtest — each was graded by a model that never saw it, so the numbers show how the model would have actually performed if it had been used on draft night. Click a year to see the picks the model nailed and the ones it whiffed on.
2015254 prospects
Top 32 overlap12 / 32
All-rounds net edge-8
20
hits
9
misses
11
saves
2016253 prospects
Top 32 overlap19 / 32
All-rounds net edge-16
17
hits
14
misses
13
saves
2017252 prospects
Top 32 overlap20 / 32
All-rounds net edge-6
18
hits
6
misses
13
saves
2018256 prospects
Top 32 overlap23 / 32
All-rounds net edge-11
43
hits
14
misses
11
saves
2019254 prospects
Top 32 overlap19 / 32
All-rounds net edge+7
34
hits
11
misses
16
saves
2020253 prospects
Top 32 overlap22 / 32
All-rounds net edge+4
42
hits
7
misses
9
saves
2021259 prospects
Top 32 overlap22 / 32
All-rounds net edge-8
35
hits
16
misses
11
saves
2022262 prospects
Top 32 overlap24 / 32
All-rounds net edge+7
35
hits
14
misses
14
saves
2023258 prospects
Top 32 overlap22 / 32
All-rounds net edge+10
Too early to grade — these careers are still unfolding. The board is on the record; the verdict comes when the players have played.
2024256 prospects
Top 32 overlap23 / 32
All-rounds net edge-3
Too early to grade — these careers are still unfolding. The board is on the record; the verdict comes when the players have played.
2025256 prospects
Top 32 overlap23 / 32
All-rounds net edge+13
Too early to grade — these careers are still unfolding. The board is on the record; the verdict comes when the players have played.
All numbers score the Draftanomics board. Top 32 overlap counts how many of the model's first-round picks the NFL also took in the first round. Net edge tallies the model's wins (hits and saves) minus its losses (misses and reaches) across all seven rounds.