Track Record

The AI's record, graded live in public

Every pick our engines publish is frozen at the moment it's called, then graded against the real final score. Nothing is edited after the fact. This dashboard is the full accounting — wins, losses, form, and whether the confidence we claimed matched the results we delivered — and it refreshes itself as games finish.

Live — refreshes automatically as games gradeUpdated Aug 6, 9:32 PM

Graded record

43-23-1

572 pending

Win rate

65.2%

over 66 decided

Net units

+17.44u

ROI +26.0% per pick

Brier score

0.233

0.250 = coin-flip guessing

Last 7 days

0-1

0.0% · -1.00u

Last 30 days

43-23-1

65.2% · +17.44u

All time

43-23-1

65.2% · +17.44u

Streak

L1

Best W8 · Worst L3

Value Model

534 pending

Deterministic value model, graded against the spread at -110.

Record
30-16-1
Win rate
65.2%
Units
+11.27u
ROI
+24.0%
Brier
0.232

GPT Engine

38 pending

LLM engine graded on its own market: spread at -110 or the real moneyline price.

Record
13-7
Win rate
65.0%
Units
+6.17u
ROI
+30.9%
Brier
0.237

Calibration: claimed vs delivered

Picks are grouped by the confidence the engine claimed at publication. A well-calibrated engine's delivered win rate tracks its claimed confidence — bars that match mean the AI knows what it knows.

Cumulative units

Net profit for each engine as its graded picks settled, in the order games actually finished.

Rolling win rate

Trailing win rate over the last 20 decided picks. Staying above 52.4% beats the standard -110 break-even.

Daily results

Wins and losses settled per day over the last 30 graded days.

Net units by league

Where the profit actually comes from. Green bars are profitable leagues; red are net losers.

Recently graded

Newest first
  • cs2Home -2Final 0-0 · Value Model · 56% conf · Aug 3, 2:00 AMLost
  • f1Home -2Final 219-169 · Value Model · 59% conf · Jul 28, 4:08 PMWon
  • dota2Away -3Final 0-0 · Value Model · 56% conf · Jul 25, 4:05 PMWon
  • cs2Home -3.5Final 0-0 · Value Model · 57% conf · Jul 25, 4:05 PMLost
  • cs2Home -1.5Final 0-0 · Value Model · 58% conf · Jul 25, 4:05 PMLost
  • cs2Away -2Final 0-0 · Value Model · 55% conf · Jul 24, 8:35 AMWon
  • dota2Away -1.5Final 0-0 · Value Model · 54% conf · Jul 23, 7:42 PMWon
  • lolAway -3Final 0-0 · Value Model · 57% conf · Jul 23, 12:46 AMWon
  • cs2Away -0.5Final 0-0 · Value Model · 60% conf · Jul 19, 7:02 PMWon
  • atpMartinez -1.5Pedro Martinez @ David Jorda Sanchis — Final 0-2 · AI Engine · 75% conf · Jul 18, 2:25 PMLost
  • wtaPalicova MLBarbora Palicova @ Mai Hontama — Final 2-0 · AI Engine · 80% conf · Jul 18, 2:19 PMWon
  • atpRocha MLFrancisco Rocha @ Gonzalo Bueno — Final 2-0 · AI Engine · 65% conf · Jul 18, 2:17 PMLost

By league

LeagueRecordWin rateUnits
mlb17-4-181.0%+12.39u
wta11-664.7%+3.82u
atp4-544.4%-1.36u
nba3-442.9%-0.66u
cs22-433.3%-2.18u
wnba2-0100.0%+1.82u
dota22-0100.0%+1.82u
f11-0100.0%+0.91u
lol1-0100.0%+0.91u

How this record is kept

  • Picks are recorded the first time they're published — the side, line, and confidence are frozen and never rewritten as the market moves.
  • Spread picks are settled against the closing score at the industry-standard -110 price; moneyline picks settle at their real quoted price.
  • The rolling win rate tracks the trailing 20 decided picks; 52.4% is the break-even threshold at -110 pricing.
  • The Brier score measures whether claimed confidence matched reality: 0 is perfect foresight, 0.250 is what pure 50/50 guessing scores. Lower is better.
  • All figures are informational analysis of our model's performance — not betting advice, and no real wagers are placed.