Glass Pitch

The ledger

Our identity is radical transparency. Every prediction is timestamped, locked at kickoff, and scored properly after full-time — wins and losses alike. The misses stay visible, permanently. See our methodology for exactly how these numbers are computed.

And you don’t have to take our word for it — every scored call is sealed into a public SHA-256 hash chain, each row locking the one before it, so any change to a past result breaks the chain in a way anyone can check. Tamper-evident, not just promised.

Running record

0.57

Mean Brier score

0 best, 2 worst — lower is better. Losses included.

0.90

Mean log loss

Punishes confident misses — lower is better.

Across 18 scored predictions — wins and losses alike. The outcome we leaned towards came in 5 of 18 (28%); every miss is counted in full.

Sample size matters. Small samples are noisy; these numbers only mean something over dozens-to-hundreds of scored predictions. We show the count alongside every metric so the record is honest about its own limits.

Calibration — checking our work

Calibration asks a simple question: when we say 30%, does it happen about 30% of the time? Each band groups every home, draw and away probability we assigned, so 18 matches give 54 data points. Well-calibrated overall — when we say 45%, it lands about 46% of the time.

Reliability diagram: predicted probability versus actual hit rateOne dot per predicted-probability band with at least one scored call, plotting the average probability we assigned on the horizontal axis against how often the outcome actually happened on the vertical axis. Dot size shows how many predictions fall in that band. A dashed diagonal line marks perfect calibration — a dot sitting on it means that probability landed exactly as often as predicted. The exact figures for every band, including empty ones, are in the table below this diagram.02550751000255075100Predicted probability (%)Actual hit rate (%)Perfect calibration0–10% band, 3 data points: we predicted 0% on average, and it happened 0% of the time.10–20% band, 13 data points: we predicted 10% on average, and it happened 8% of the time.30–40% band, 6 data points: we predicted 33% on average, and it happened 33% of the time.40–50% band, 26 data points: we predicted 45% on average, and it happened 46% of the time.50–60% band, 6 data points: we predicted 50% on average, and it happened 50% of the time.
Each dot is one predicted-probability band with at least one scored call; size shows how many predictions sit in that band. A dot on the dashed line means that probability landed exactly as often as we said. Full numbers for every band, including empty ones, are in the table.
Calibration by predicted-probability band: how many probabilities fell in each band, the average we predicted, and how often the outcome actually happened.
Confidence bandData pointsWe predictedIt happened
0–10%30%0%
10–20%1310%8%
20–30%0
30–40%633%33%
40–50%2645%46%
50–60%650%50%
60–70%0
70–80%0
80–90%0
90–100%0

Every scored call

Every scored prediction, newest first: the outcome we leaned towards, the kickoff date, the actual score and that call’s Brier score. Lower Brier is better.
ResultMatchDateScoreBrier
Spain v ArgentinaOur call: Spain (45%)0–00.52
France v EnglandOur call: France (45%)4–61.22
England v ArgentinaOur call: the draw (45%)1–20.52
France v SpainOur call: the draw (45%)0–20.52
Argentina v SwitzerlandOur call: Argentina (45%)1–10.52
Norway v EnglandOur call: the draw (45%)1–10.52
Spain v BelgiumOur call: Spain (45%)2–10.52
France v MoroccoOur call: France (45%)2–00.52
Switzerland v ColombiaOur call: Switzerland (35%)0–00.64
Argentina v EgyptOur call: Argentina (45%)3–20.52
USA v BelgiumOur call: the draw (45%)1–40.52
Portugal v SpainOur call: the draw (45%)0–10.52
Brazil v NorwayOur call: Brazil (35%)1–20.73
Paraguay v FranceOur call: the draw (50%)0–10.50
Canada v MoroccoOur call: the draw (45%)0–30.52
Colombia v GhanaOur call: Colombia (50%)1–00.50
Argentina v Cape Verde IslandsOur call: Argentina (50%)1–10.50
Australia v EgyptOur call: Australia (45%)1–10.52

Newest first. Lower Brier is better (0 to 2). Tap any match for its full breakdown, including log loss.

Probabilities from a third-party model; context, not a guarantee.

Analysis and probabilities only — not betting advice. Outcomes are uncertain; we do not guarantee results and we do not claim to beat the market.