4.0M+ predictions logged and growing. Leading model results published — wins and losses.
For each sport and market where a model earns live status through verified results, its selections are published to our Telegram channel. Timestamped, unedited, permanent. Wins and losses both stay. Nothing deleted or revised.
| Date | Sport | Market | Selection | Odds | Result | P&L (units) |
|---|---|---|---|---|---|---|
| No published selections yet. First alerts go out when the model detects a live divergence. | ||||||
All figures use a flat 1-unit notional stake per selection at the odds published to our Telegram channel. P&L is reported in units (1 unit = AUD $100 notional). Results reflect the selections exactly as published — wins and losses included without cherry-picking. Tracking commenced 20 May 2026 . These figures do not account for bookmaker account limitations, odds movement, or liquidity. Informational only. Not financial or gambling advice.
We run 13 independent models in parallel across every sport. The table below shows the all-time paper trading record for every (sport, market, model) combination — wins, losses, strike rate, ROI. No cherry-picking.
| Sport | Market | Model | Record (W-L) | Strike rate | ROI |
|---|---|---|---|---|---|
| AFL | Spreads | Model F | 31-22 | 58.5% | +12.8% |
| AFL | Spreads | Model A | 30-23 | 56.6% | +10.2% |
| AFL | Spreads | Model B | 29-23 | 55.8% | +8.3% |
| AFL | Spreads | Model D | 28-26 | 51.9% | +0.2% |
| AFL | Totals | Model E | 29-23 | 55.8% | +5.9% |
| AFL | Totals | Model H | 28-23 | 54.9% | +4.3% |
| Bundesliga | H2H | Model H | 22-31 | 41.5% | +34.2% |
| Bundesliga | H2H | Model G | 23-31 | 42.6% | +20.1% |
| Bundesliga | H2H | Model C | 16-34 | 32.0% | +20.0% |
| Bundesliga | Totals | Model M | 31-19-4 | 62.0% | +24.1% |
| Bundesliga | Totals | Model A | 27-21-3 | 56.2% | +15.2% |
| Bundesliga | Totals | Model D | 27-24-3 | 52.9% | +10.7% |
| EPL | H2H | Model F | 15-37 | 28.8% | +17.5% |
| EPL | H2H | Model A | 18-33 | 35.3% | +16.0% |
| EPL | H2H | Model B | 20-34 | 37.0% | +4.9% |
| EPL | H2H | Model E | 16-34 | 32.0% | +1.6% |
| EPL | Spreads | Model A | 32-13-10 | 71.1% | +20.3% |
| EPL | Spreads | Model M | 29-17-10 | 63.0% | +9.2% |
| EPL | Spreads | Model E | 23-21-7 | 52.3% | +4.6% |
| EPL | Totals | Model B | 37-19-5 | 66.1% | +33.7% |
| EPL | Totals | Model A | 33-21-5 | 61.1% | +24.6% |
| EPL | Totals | Model M | 31-22-4 | 58.5% | +19.5% |
| La Liga | H2H | Model H | 21-34 | 38.2% | +26.7% |
| La Liga | H2H | Model E | 24-27 | 47.1% | +26.4% |
| La Liga | H2H | Model I | 17-34 | 33.3% | +20.5% |
| La Liga | H2H | Model A | 23-37 | 38.3% | +19.6% |
| La Liga | H2H | Model G | 28-37 | 43.1% | +11.3% |
| La Liga | H2H | Model M | 19-42 | 31.1% | +7.4% |
| La Liga | Totals | Model G | 29-26-2 | 52.7% | +13.2% |
| La Liga | Totals | Model J | 32-29-2 | 52.5% | +9.5% |
| MLB | H2H | Model F | 64-82 | 43.8% | +5.5% |
| MLB | H2H | Model C | 53-66-1 | 44.5% | +3.5% |
| MLB | H2H | Model E | 92-105-1 | 46.7% | +0.2% |
| MLB | Spreads | Model E | 87-80-6 | 52.1% | +17.4% |
| MLB | Spreads | Model I | 136-179-1 | 43.2% | +4.2% |
| MLB | Spreads | Model H | 147-166-7 | 47.0% | +3.7% |
| MLB | Spreads | Model A | 136-182-5 | 42.8% | +2.6% |
| MLB | Spreads | Model K | 77-107-3 | 41.8% | +1.3% |
| MLB | Totals | Model A | 126-119-14 | 51.4% | +2.3% |
| MLB | Totals | Model B | 111-121-8 | 47.8% | +0.2% |
| NBA | H2H | Model D | 21-38 | 35.6% | +40.6% |
| NBA | H2H | Model G | 41-48 | 46.1% | +40.6% |
| NBA | H2H | Model J | 18-43 | 29.5% | +27.4% |
| NBA | H2H | Model E | 37-52 | 41.6% | +18.4% |
| NBA | H2H | Model C | 36-51 | 41.4% | +14.5% |
| NBA | H2H | Model A | 43-50 | 46.2% | +4.8% |
| NBA | H2H | Model I | 32-58 | 35.6% | +4.2% |
| NBA | H2H | Model B | 30-30 | 50.0% | +2.4% |
| NBA | H2H | Model M | 47-56 | 45.6% | +0.3% |
| NBA | Spreads | Model G | 30-34 | 46.9% | +9.3% |
| NBA | Spreads | Model F | 35-36 | 49.3% | +5.2% |
| NBA | Spreads | Model I | 37-38 | 49.3% | +2.7% |
| NBA | Spreads | Model K | 28-28-1 | 50.0% | +0.1% |
| NBA | Totals | Model G | 36-28 | 56.2% | +22.3% |
| NBA | Totals | Model E | 37-24 | 60.7% | +17.0% |
| NBA | Totals | Model B | 39-31 | 55.7% | +14.3% |
| NBA | Totals | Model J | 37-31 | 54.4% | +11.3% |
| NBA | Totals | Model M | 40-36 | 52.6% | +6.2% |
| NBA | Totals | Model L | 38-37 | 50.7% | +2.4% |
| NBA | Totals | Model A | 36-35 | 50.7% | +1.8% |
| NHL | H2H | Model E | 67-60 | 52.8% | +8.1% |
| NHL | H2H | Model B | 50-44 | 53.2% | +5.1% |
| NHL | H2H | Model I | 48-54 | 47.1% | +4.7% |
| NHL | Spreads | Model J | 35-40-4 | 46.7% | +13.3% |
| NHL | Spreads | Model D | 42-48-2 | 46.7% | +5.5% |
| NHL | Spreads | Model E | 36-26-2 | 58.1% | +5.3% |
| NHL | Spreads | Model K | 27-24-1 | 52.9% | +2.9% |
| NHL | Totals | Model J | 40-38-5 | 51.3% | +4.3% |
| NHL | Totals | Model F | 33-31-3 | 51.6% | +4.3% |
| NHL | Totals | Model D | 45-44-5 | 50.6% | +3.4% |
| NHL | Totals | Model H | 44-42-5 | 51.2% | +2.0% |
| NHL | Totals | Model C | 35-38-3 | 47.9% | +1.0% |
| NRL | H2H | Model H | 28-22 | 56.0% | +23.4% |
Data current as of May 2026 . Every (sport, market, model) combination with ≥10 settled paper bets is shown. No "leading model" cherry-picking.
All figures are based on simulated paper trading — not real-money wagering. Each prediction is recorded with a flat notional stake of AUD $100 at the best available global bookmaker odds at prediction time. ROI is calculated as total simulated profit or loss divided by total notional amount staked. These figures do not account for bookmaker account limitations, odds movement between prediction and placement, market liquidity, or other real-world execution factors. Actual results could differ materially from the reported figures. Paper trading since February 2026.
We build statistical models that analyse sports data. Here is exactly what they do, what they cannot do, and why we tell you both.
Our 13 independent models ingest historical match data, team performance statistics, and real-time bookmaker odds across 16 sports. Each model uses a different statistical methodology to estimate outcome probabilities. When a model's probability diverges significantly from the market's implied probability, we flag it and publish the analysis.
Every model runs independently -- no shared predictions, no committee decisions. We track each model's accuracy by sport and market type over time. The model with the strongest verified track record in a given sport earns the right to generate subscriber alerts. Models that underperform lose their reporting slot. The data decides, not us.
Models are retrained as new data accumulates. New statistical approaches are tested in shadow mode -- logging predictions without generating alerts -- until they demonstrate sustained accuracy against real market odds.
Each model uses a different statistical approach — running independently, with no shared predictions, using real-time odds from multiple bookmakers.
Every market is scanned for statistical divergence. An alert is generated only when a model's calculated probability exceeds the bookmaker's implied probability by at least 5%. Data, not opinion.
Each sport and market combination is tracked across all 13 models. Only the most accurate model generates your alerts — and it must earn that position with verified results.
Model alerts are published the moment a divergence is identified — with the probability, the odds, and the data behind it. Premium subscribers also see the consensus score: how many of the 13 models agree.
Follow the public channel to see real model analysis in real time before subscribing. No credit card. No commitment.
We're building something different — rigorous, transparent AI sports analytics with a verified track record. Register your interest to be among the first to access gpunt when we launch Foundation Subscriptions.