TACTIX publishes how good its model is — measured, not claimed. Our headline is calibration: when we say 60%, it should happen about 60% of the time. This page updates from settled results.
Predicted probability (x) vs the rate those outcomes actually occurred (y), across all settled predictions. The closer to the dashed diagonal, the better calibrated.
Loading live calibration…
Each dot pools every settled prediction made at a given confidence level. Its position answers one question: when the model said "X% likely", how often did that outcome actually happen? A dot at x = 0.70, y = 0.69 means outcomes the model priced at 70% occurred 69% of the time. The dashed diagonal is perfection; the further a dot sits from it, the more the model over- or under-states that probability band. The headline figure — ±0.7% across 8M+ settled predictions — is the average of those gaps, weighted by sample.
Two honest caveats baked into this page: sparse cells (small samples) are flagged rather than celebrated, and profit columns include the negative numbers — calibration says the probabilities are truthful, not that every market beats the bookmaker's margin. Terms are defined in the glossary; the method itself is on the methodology page.
The live figures at the top of this page are the answer, recomputed as predictions settle: the sample size and mean calibration error update continuously. When the model says 60%, the reliability curve shows how close to 60% reality lands — that correspondence, not a headline win rate, is what calibration measures.
A single accuracy number is easy to inflate and mostly reflects how predictable a league or market is. Calibration measures whether the stated probabilities are honest across every prediction — including the unglamorous ones — and it can be verified from the downloads on this page.
Yes — the per-league, per-market breakdown on this page exports as CSV or JSON with the buttons above, and the same data is served by the public API. Check the numbers, don't take them on trust.
No. Calibration means the probabilities are truthful; profit additionally depends on finding prices that disagree with those probabilities by more than the bookmaker's margin, and on variance over a long sample. The ROI columns in the breakdown — negatives included — make that distinction visible. 18+, gamble responsibly.
Calibration error for every league and market we cover — losers included, no cherry-picking. Lower is better: ±2% means that when we say 60%, it lands about 58–62% of the time. Filter by league, market and window. The ROI column flat-stakes the model’s top pick at the closing price (the last price recorded before kick-off) — most markets sit negative (the bookmaker’s margin); green is where an edge showed.
Loading the by-market record…
One published base model, then per-market calibration, a dedicated calibrated three-way match-result model (expected goals + team Elo) and a validated stacking layer for the markets where it measurably helps. Every change is validated out-of-time before it ships.
More on the build in our methodology & editorial standards. Model vs the bookmaker favourite, league by league: the accuracy leaderboard.
18+Calibration and accuracy figures are measured on settled predictions and are not a guarantee of future results; nothing here is betting advice. Please gamble responsibly — BeGambleAware.org.