Every completed game across MLB, NBA, WNBA, NHL, NFL, and NCAA. Each prediction is logged before the game finishes; the result is whatever happened. No cherry-picking, no hindsight edits. Refreshed every 5 minutes.
Live model health · 30-day window
Drift fires when the last 30 days' Brier score exceeds the prior 90-day baseline by more than 0.025. When a market drifts, picks pause automatically until the next snapshot clears it. Snapshots refresh on an hourly cron. r363 — this strip mirrors the same data the auto-pause banner reads, surfaced here as a public-facing receipt.
RELIABILITY · PREDICTED vs OBSERVED
X · MODEL SAID Y · ACTUALLY WON n=6,990
6,990 picks · 9 buckets
| Predicted | Actual win rate | Sample | 95% CI | Verdict |
|---|---|---|---|---|
| 50 to 55% | 52.8% | 1381 of 2615 | 51–55% | calibrated |
| 55 to 60% | 55.3% | 1233 of 2230 | 53–57% | overconfident |
| 60 to 65% | 61.6% | 773 of 1255 | 59–64% | calibrated |
| 65 to 70% | 68.1% | 356 of 523 | 64–72% | calibrated |
| 70 to 75% | 73.7% | 165 of 224 | 68–79% | calibrated |
| 75 to 80% | 78.8% | 63 of 80 | 69–86% | calibrated |
| 80 to 85% | 90.9% | 40 of 44 | 79–96% | calibrated |
| 85 to 90% | 94.4% | 17 of 18 | 74–99% | calibrated |
| 90% or higher | 0.0% | 0 of 1 | 0–79% | overconfident |
When the model said ~53%, those picks won 52.8% (1381/2615) — inside the 95% noise band.
Accuracy windows · cross-sport
Last 7 days
60.0%
66 / 110 games
Last 30 days
59.4%
256 / 431 games
Last 90 days
61.2%
882 / 1441 games
All-time
+1.0 pts
1575/21505 priced · raw 66.7%
By league · last 30 days
Spread receipts · NCAA
Posted spreads only. No price invented.
50.0%
1,074 decided · 52.4% breaks even at -110
52-46-3 ATS
53.1% cover rate
30D reliability
n=98 · ECE 0.083 · Brier 0.249
485-491 ATS
49.7% cover rate
30D reliability
n=976 · ECE 0.086 · Brier 0.259
By model confidence · all-time · cross-sport
Locks
Highest model conviction
81%5400/6684
Edges
Strong lean
68%4125/6088
Leans
Modest lean
57%2764/4809
Tossups
Near coin-flip
53%2065/3924
Higher-conviction tiers should hit at higher rates. If they don't, the model is poorly calibrated — the table tells the truth either way. Tier thresholds tuned per league (NHL tighter than NBA / MLB / WNBA).
What this model is — and isn't
It's accurate and well-calibrated. It wins more than 6 in 10 outright, and when it says 70% those picks land near 70% — that's our Calibration Grade, the receipt we lead with.
It does not consistently beat the closing line. Our closing-line value runs slightly negative — by kickoff the market, on average, prices these games a hair sharper than the model does. Calibration and market-beating are different things, and we're straight about which one we've earned.
Most services bury this number. We publish it, in full, right below. Receipts, not picks.
Vs market · cross-sport · 2,853 games on closing lines
Agreed with Vegas
Model picked the closing favorite
Disagreed (the edge bets)
Model picked the closing underdog
Agree
59.5% 654/1099
Disagree
57.1% 276/483
Agree
71.4% 25/35
Disagree
60.0% 12/20
Agree
74.2% 118/159
Disagree
52.4% 22/42
Agree
56.7% 421/742
Disagree
48.7% 133/273
Disagreement bucket = bets where the model picked the underdog at the closing line. If that row hits above ~46%, the model would be +EV against the closing price assuming standard −110-equivalent juice. WNBA absent — ESPN's WNBA pickcenter doesn't ship closing spreads consistently. Pure CLV (cents won vs closing moneyline) is below — see the “Pure CLV” panel.
Pure CLV · cross-sport · 1,942 graded picks
Avg CLV
+383
basis points
Median CLV
+336
basis points
Positive %
6802.0%
picks beat the close
Per 100u
-1262285¢
cents · normalized
Sharp
301 picks
+1276
10000% positive
High
149 picks
+473
9866% positive
Medium
752 picks
+796
9907% positive
Low
740 picks
-417
1730% positive
CLV = the price we issued vs the closing line at game start. +100 bps means we got +1c better than the close on average. A sustained positive CLV is the cleanest forward-signal that the model is finding real edge — it's independent of whether any individual pick cashed. r298 ingest writes one row per settled pick; this panel is the all-time cross-sport view.
Edge honesty · 1,942 graded picks · 1077 price-less excluded
FLAT 1u STAKE · WIN% INCLUDES PUSHES (DISCLOSED) · THIN BUCKETS (n < 30) DIMMED, NOT HIDDEN
By closing-line value
clv_bps vs the close
| Bucket | n | Win% | Avg price | ROI |
|---|---|---|---|---|
| < −100 bps | 546 | 57.9% | -181 | -7.9% |
| −100 – 0 | 75 | 72% | -145 | +25% |
| 0 – 100 | 83 | 61.4% | -122 | +9% |
| 100 – 250 | 171 | 52% | -112 | -8.5% |
| ≥ 250 bps | 1067 | 52.5% | -66 | -3% |
By modeled edge
edge_bps at log time
| Bucket | n | Win% | Avg price | ROI |
|---|---|---|---|---|
| < 200 bps | 740 | 58.9% | -168 | -3.5% |
| 200 – 400 | 175 | 56.6% | -101 | +0.9% |
| 400 – 700 | 398 | 52.8% | -91 | -6.1% |
| ≥ 700 bps | 629 | 51.7% | -50 | -2.4% |
By confidence tier
producer-assigned
| Bucket | n | Win% | Avg price | ROI |
|---|---|---|---|---|
| sharp | 301 | 53.8% | -17 | +6% |
| high | 149 | 43.6% | -71 | -20.6% |
| medium | 752 | 54.1% | -93 | -3.4% |
| low | 740 | 58.9% | -168 | -3.5% |
Unsmoothed, straight off the picks ledger. As of this build the CLV→cash gradient is NOT clean — the deep-negative bucket is heavy favorites at negative ROI and the middle buckets are thin. That result is published, not curated.
Edge honesty · 1,942 graded picks · 1077 missing a price, dropped from both series
FLAT 1u PER PICK · LOSSES −1 AT BOTH PRICES (ONLY WINNING PAYOUTS DIFFER) · SAME PICK SET, TWO PRICES
Timing alpha
-20.2u
At our price
-64.0u
At the close
-43.8u
Max drawdown
−84.5u
Streaks
W16 / L9
— at our logged price·— at the close
The exact same picks, graded at the price we logged vs the closing price. Positive alpha would mean betting at publish beat betting at close — as of this build it is negative, and that ships too. Drawdown and streaks are on the logged series.
Bet-history simulator · cross-sport
Bankroll simulator · $100 per pick
Ending bankroll
$6796
Net profit
+$5796
ROI
13.4%
Picks
431
Simulates $100 per pick at standard −110 juice (+$91 win, −$100 loss) on every completed cross-sport model pick in the window. Real betting layers in book vig variance, line shopping, and bet-sizing — this is the "follow every pick flat" baseline.
Last 30 days · daily hit rate · cross-sport
431 games · 256 correct · 59.4%
50% baseline ←→ 100%
Where to play
21+ · Bet responsibly · 1-800-GAMBLER
Predictions logged at game start · results compared to actual outcomes · no editing after the fact. Bet responsibly · 21+ · 1-800-GAMBLER
Last night's record — wins and losses alike — plus tonight's slate. Free, double opt-in, one click to leave.