Insights · NFL

What happened. What we learned.

Every graded pick, wins and losses, in one place. Read the record beside the proof, then see which angles held up.

Leaderboard · hit rate by lens

Leaderboard · models against the favourite baseline

Headline performance is ATS spread win rate. Pushes remain in graded spread plays but are excluded from the ATS spread denominator.

Rows are ordered by spread win rate; closing-line value breaks ties when available.
Entry	Kind	Graded spread plays	ATS spread win rate	Record (W-L-P)	CLV · secondary
[Auto] NFL Spread (MARS) n=47 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	47	61.7% · n=47 Live picks · all time · n=47 · through Oct 12, 12:08 AM ET	29-18-0	−0.021
[Auto] NFL Spread (MARS) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	57.9% · n=57 Live picks · all time · n=57 · through Oct 12, 12:08 AM ET	33-24-21	+0.526
[Auto] Blueprint (Py): Momentum Spread Model (ElasticNet) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	55.4% · n=65 Live picks · all time · n=65 · through Oct 12, 12:08 AM ET	36-29-13	+0.032
[Auto] NFL Elo Power Ratings Spread (XGBoost) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	54.2% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	32-27-0	+0.025
model-3950f12e n=24 graded spread plays · as of 2026-09-22T03:34:00.49759+00:00	model	24	54.2% · n=24 Live picks · all time · n=24 · through Sep 21, 11:34 PM ET	13-11-0	+0.250
[Auto] NFL Spread (KNN) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	53.7% · n=54 Live picks · all time · n=54 · through Oct 12, 12:08 AM ET	29-25-24	+0.282
[Auto] NFL Spread (SVR) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	53.4% · n=58 Live picks · all time · n=58 · through Oct 12, 12:08 AM ET	31-27-20	+0.359
[Auto] NFL Spread (ExtraTrees) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	52.8% · n=53 Live picks · all time · n=53 · through Oct 12, 12:08 AM ET	28-25-25	+0.077
[Auto] NFL Elo Power Ratings Spread (XGBoost) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	52.4% · n=63 Live picks · all time · n=63 · through Oct 12, 12:08 AM ET	33-30-15	+0.077
[Auto] Blueprint (Py): Momentum Spread Model (XGB) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	51.7% · n=60 Live picks · all time · n=60 · through Oct 12, 12:08 AM ET	31-29-18	+0.032
[Auto] Blueprint (Py): Full Feature Spread (Stacking Ensemble) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	50.9% · n=53 Live picks · all time · n=53 · through Oct 12, 12:08 AM ET	27-26-25	+0.455
[Auto] NFL Spread (KNN) n=57 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	57	50.9% · n=57 Live picks · all time · n=57 · through Oct 12, 12:08 AM ET	29-28-0	−0.044
[Auto] NFL ATS XGBoost (Custom Objective) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	50.0% · n=60 Live picks · all time · n=60 · through Oct 12, 12:08 AM ET	30-30-18	+0.269
[Auto] Blueprint (Py): Turnover Regression Model (ElasticNet) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	50.0% · n=54 Live picks · all time · n=54 · through Oct 12, 12:08 AM ET	27-27-24	+0.256
[Auto] Playbook (Py): Full Feature Spread (Stacking Ensemble) n=58 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	58	50.0% · n=58 Live picks · all time · n=58 · through Oct 12, 12:08 AM ET	29-29-0	+0.017
[Auto] NFL Spread (SVR) n=75 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	75	49.3% · n=75 Live picks · all time · n=75 · through Oct 12, 12:08 AM ET	37-38-0	+0.013
[Auto] NFL GNN Matchup n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	49.2% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	29-30-0	+0.110
[Auto] NFL Spread Stacking n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	49.2% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	29-30-0	+0.068
[Auto] NFL Spread (HistGradientBoosting) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	49.1% · n=55 Live picks · all time · n=55 · through Oct 12, 12:08 AM ET	27-28-23	+0.103
[Auto] NFL Spread Stacking n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	48.4% · n=62 Live picks · all time · n=62 · through Oct 12, 12:08 AM ET	30-32-16	+0.359
[Auto] Playbook (Py): Full Feature Spread (Mixture of Experts) n=58 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	58	48.3% · n=58 Live picks · all time · n=58 · through Oct 12, 12:08 AM ET	28-30-0	+0.017
[Auto] NFL GNN Matchup n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	48.1% · n=54 Live picks · all time · n=54 · through Oct 12, 12:08 AM ET	26-28-24	+0.449
[Auto] Blueprint (Py): Full Feature Spread (XGB) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	47.5% · n=61 Live picks · all time · n=61 · through Oct 12, 12:08 AM ET	29-32-17	+0.327
[Auto] Blueprint (Py): Pressure & Efficiency Model (LightGBM) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	47.5% · n=61 Live picks · all time · n=61 · through Oct 12, 12:08 AM ET	29-32-17	+0.077
[Auto] Blueprint (Py): Full Feature Spread (Mixture of Experts) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	47.5% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	28-31-0	+0.093
[Auto] NFL ATS XGBoost (Custom Objective) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	47.5% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	28-31-0	0.000
model-4cbee016 n=40 graded spread plays · as of 2026-10-12T00:08:05.379284+00:00	model	40	47.2% · n=36 Live picks · all time · n=36 · through Oct 11, 8:08 PM ET	17-19-4	+0.225
model-1758a821 n=30 graded spread plays · as of 2026-09-23T05:56:07.815427+00:00	model	30	46.7% · n=30 Live picks · all time · n=30 · through Sep 23, 1:56 AM ET	14-16-0	+0.200
[Auto] NFL Minimal Signal Spread (XGBoost) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	46.6% · n=58 Live picks · all time · n=58 · through Oct 12, 12:08 AM ET	27-31-20	+0.103
[Auto] NFL Spread (AdaBoost) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	46.4% · n=56 Live picks · all time · n=56 · through Oct 12, 12:08 AM ET	26-30-22	+0.179
[Auto] Blueprint (Py): Pressure & Efficiency Model (LightGBM) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	45.5% · n=77 Live picks · all time · n=77 · through Oct 12, 12:08 AM ET	35-42-1	+0.122
[Auto] Blueprint (Py): Momentum Spread Model (ElasticNet) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	45.5% · n=77 Live picks · all time · n=77 · through Oct 12, 12:08 AM ET	35-42-1	+0.058
[Auto] Blueprint (Py): Full Feature Spread (Mixture of Experts) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	45.3% · n=53 Live picks · all time · n=53 · through Oct 12, 12:08 AM ET	24-29-25	+0.205
[Auto] Blueprint (Py): Full Feature Spread (XGB) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	44.8% · n=58 Live picks · all time · n=58 · through Oct 12, 12:08 AM ET	26-32-20	+0.397
[Auto] NFL MLP Spread n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	44.6% · n=56 Live picks · all time · n=56 · through Oct 12, 12:08 AM ET	25-31-22	+0.295
[Auto] NFL Market Efficiency Spread (XGBoost) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	44.6% · n=56 Live picks · all time · n=56 · through Oct 12, 12:08 AM ET	25-31-22	+0.103
[Auto] NFL Multi-Task Spread n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	44.3% · n=61 Live picks · all time · n=61 · through Oct 12, 12:08 AM ET	27-34-17	+0.410
[Auto] Playbook (Py): Feature Store Spread Model (XGB) n=43 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	43	44.2% · n=43 Live picks · all time · n=43 · through Oct 12, 12:08 AM ET	19-24-0	+0.023
[Auto] Playbook (Py): Full Feature Spread (XGB) n=43 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	43	44.2% · n=43 Live picks · all time · n=43 · through Oct 12, 12:08 AM ET	19-24-0	+0.023
[Auto] Playbook (Py): Momentum Spread Model (XGB) n=43 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	43	44.2% · n=43 Live picks · all time · n=43 · through Oct 12, 12:08 AM ET	19-24-0	+0.023
[Auto] Blueprint (Py): Turnover Regression Model (ElasticNet) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	44.2% · n=77 Live picks · all time · n=77 · through Oct 12, 12:08 AM ET	34-43-1	+0.250
[Auto] Blueprint (Py): Turnover Regression Model (ElasticNet) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	44.2% · n=77 Live picks · all time · n=77 · through Oct 12, 12:08 AM ET	34-43-1	+0.237
[Auto] NFL MLP Spread n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	44.1% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	26-33-0	+0.008
[Auto] NFL Spread (Gaussian Process) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	44.1% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	26-33-0	+0.008
[Auto] NFL Spread (CatBoost) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	44.1% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	26-33-0	−0.068
[Auto] Blueprint (Py): SHAP Explainable Elo Model (Linear) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	43.5% · n=62 Live picks · all time · n=62 · through Oct 12, 12:08 AM ET	27-35-16	+0.096
[Auto] NFL Spread (Gaussian Process) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	42.4% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	25-34-19	+0.333
[Auto] Playbook (Py): Momentum Spread Model (ElasticNet) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	42.4% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	25-34-0	+0.042
[Auto] NFL Spread (ExtraTrees) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	42.4% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	25-34-0	0.000
[Auto] Blueprint (Py): Full Feature Spread (Stacking Ensemble) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	41.8% · n=55 Live picks · all time · n=55 · through Oct 12, 12:08 AM ET	23-32-23	+0.359
[Auto] Blueprint (Py): Simple Elo Spread Model (Linear) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	41.5% · n=65 Live picks · all time · n=65 · through Oct 12, 12:08 AM ET	27-38-13	+0.058
[Auto] Blueprint (Py): SHAP Explainable Elo Model (Linear) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	40.3% · n=77 Live picks · all time · n=77 · through Oct 12, 12:08 AM ET	31-46-1	+0.135
[Auto] Blueprint (Py): Simple Elo Spread Model (Bayesian) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	39.3% · n=56 Live picks · all time · n=56 · through Oct 12, 12:08 AM ET	22-34-22	+0.096
[Auto] NFL Multi-Task Spread n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	39.0% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	23-36-0	+0.068
[Auto] Playbook (Py): Turnover Regression Model (ElasticNet) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	39.0% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	23-36-0	+0.042
[Auto] NFL Spread (HistGradientBoosting) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	39.0% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	23-36-0	+0.025
[Auto] Playbook (Py): Pressure & Efficiency Model (LightGBM) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	39.0% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	23-36-0	−0.068
[Auto] Blueprint (Py): Pressure & Efficiency Model (LightGBM) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	39.0% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	23-36-0	−0.076
[Auto] Blueprint (Py): Simple Elo Spread Model (Linear) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	39.0% · n=77 Live picks · all time · n=77 · through Oct 12, 12:08 AM ET	30-47-1	+0.096
[Auto] Blueprint (Py): Simple Elo Spread Model (Bayesian) n=78 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	78	38.2% · n=55 Live picks · all time · n=55 · through Oct 12, 12:08 AM ET	21-34-23	+0.141
[Auto] Playbook (Py): Simple Elo Spread Model (Bayesian) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	37.3% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	22-37-0	−0.102
[Auto] Playbook (Py): SHAP Explainable Elo Model (Linear) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	37.3% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	22-37-0	−0.110
[Auto] NFL Spread (AdaBoost) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	35.6% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	21-38-0	+0.025
[Auto] Sharkai Starter: NFL Spread n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	35.6% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	21-38-0	−0.025
[Auto] Playbook (Py): Simple Elo Spread Model (Linear) n=59 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	59	35.6% · n=59 Live picks · all time · n=59 · through Oct 12, 12:08 AM ET	21-38-0	−0.068
[Auto] NFL Market Efficiency Spread (XGBoost) n=43 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	43	32.6% · n=43 Live picks · all time · n=43 · through Oct 12, 12:08 AM ET	14-29-0	−0.163
[Auto] NFL Minimal Signal Spread (XGBoost) n=43 graded spread plays · as of 2026-10-12T04:08:00.3326+00:00	model	43	30.2% · n=43 Live picks · all time · n=43 · through Oct 12, 12:08 AM ET	13-30-0	−0.035
[Auto] MLB Run Line (Gaussian Process) n=115 graded spread plays · as of 2026-05-20T09:00:00.606554+00:00	model	115	—	0-0-115	—
[Auto] MLB Run Line (HistGradientBoosting) n=115 graded spread plays · as of 2026-05-20T09:00:00.606554+00:00	model	115	—	0-0-115	—
[Auto] Soccer Spread (Gaussian Process) n=20 graded spread plays · as of 2026-09-02T02:48:08.572892+00:00	model	20	—	0-0-20	—
[Auto] Soccer Spread (HistGradientBoosting) n=20 graded spread plays · as of 2026-09-02T02:48:08.572892+00:00	model	20	—	0-0-20	—
[Auto] Soccer Spread (KNN) n=20 graded spread plays · as of 2026-09-02T02:48:08.572892+00:00	model	20	—	0-0-20	—
[Auto] Soccer Spread (MARS) n=20 graded spread plays · as of 2026-09-02T02:48:08.572892+00:00	model	20	—	0-0-20	—
[Auto] NHL Puck Line (Gaussian Process) n=7 graded spread plays · as of 2026-08-28T01:40:30.487538+00:00	model	7	—	0-0-7	—
[Auto] NHL Puck Line (HistGradientBoosting) n=7 graded spread plays · as of 2026-08-28T01:40:30.487538+00:00	model	7	—	0-0-7	—
[Auto] NBA Elo Power Ratings Spread (XGBoost) n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (AdaBoost) n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (Gaussian Process) n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (HistGradientBoosting) n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (KNN) n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (MARS) n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (SVR) n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
Market consensus baseline · bet every favourite n=7,324 graded spread plays · as of 2026-10-12	baseline	7,324	48.7% · n=7,123 Backtest · all time · n=7,123 · through Oct 12, 2026	3469-3654-201	—

The baseline bets every favourite against the spread across past games. It has no closing-line value, so that cell stays empty.

Not ranked yet, no graded spread picks on record: community lens, pundit, crew.

Unlock more Insights tools

Keep exploring for free, or unlock the complete Insights toolkit with Pro.

$1 first week, then $2.99/week.

See Pro

Insights · real claim grader

The graded field: the market, mined

Every pundit claim in the transcript corpus, typed and graded against what actually happened. Who has been right, who has enough evidence to judge, and where the observed field sits against the house sample and fade gates.

24 decided grades across 1 real sources · all-time window · small samples are labeled as such. Coverage: top-decile and quadrant labels describe only the currently graded field, not ungraded or unresolved calls.

Claims graded as of Oct 7, 3:54 AM ET · Source registry as of Oct 8, 3:15 AM ET

Pundit claim grading

newest 6 decided claims · same rows as the ledger

Claim	Source	Verdict
“but I'm still gonna pick the Ravens.”	Ben Solak (The Football Show) · Oct 29	wrong
“I'm gonna pick the Bills.”	Ben Solak (The Football Show) · Oct 29	correct
“I still think that the Rams have a better chance because of their consistency.”	Ben Solak (The Football Show) · Oct 29	wrong
“I still think the Jets would be able to win.”	Ben Solak (The Football Show) · Oct 29	correct
“I'm gonna pick the Browns.”	Ben Solak (The Football Show) · Oct 29	wrong
“I'm gonna pick the Raiders.”	Ben Solak (The Football Show) · Oct 29	wrong

Pundit ledger

Decided, transcript-backed calls by real source. Pushes and unresolved claims never enter the hit-rate denominator.

correct and wrong calls only quoted from the transcript

Source	W-L	Hit %	n	Window	Verdict
Ben Solak (The Football Show)	14-10	58.3%	24	all-time	hot

24 decided grades across 1 real sources · all-time window

Verdict rules: unproven below n=20; gasbag below 45% after the gate; hot is the top decile of the gated field. With a thin gated field, hot is field-relative coverage, not a claim about ungraded calls.

Gasbag quadrant

More decided claims move right; a higher correct/wrong hit rate moves up. Every dot is a directly labeled real source.

correct + wrong only all-time

Counterfactual boundary: the guide lines classify observed grades only; they do not infer how a source would have performed on unresolved or unmade calls.