The forecast. The timestamp. The result.

Explore retained forecast versions and see how their probabilities performed after the final whistle.

Browse forecasts ↓ See the full track record →

Original probabilities stay unchanged. Results are graded separately. The archive starts when retention was enabled; earlier forecasts are not reconstructed.

Public calibration - frozen forecasts

Latest 500 completed fixtures with retained forecasts; one latest retained pre-match version per fixture. Includes all model versions shown below. No reconstructed forecasts enter this report.

496graded matches

0.5492Multiclass Brier (0–2)

0.9338Log loss

500 considered · 0 awaiting results · 4 excluded: provenance or result could not be verified

Show the calibration table

Calibration across home, draw and away outcomes
Probability band	Mean predicted	Observed frequency	Outcome observations
0–10%	6.9%	11.0%	73
10–20%	15.8%	12.3%	228
20–30%	24.6%	23.5%	527
30–40%	34.9%	33.3%	228
40–50%	44.6%	45.7%	162
50–60%	54.6%	59.3%	123
60–70%	64.7%	71.2%	66
70–80%	75.5%	76.8%	56
80–90%	85.0%	90.9%	22
90–100%	94.6%	100.0%	3

Each match contributes three outcome observations; these are correlated, not three independent matches. Bands include the lower bound and exclude the upper bound, except 100%. Sparse bins are unstable. Lower Brier and log loss are better.

Model versions: v5 (495) · Earlier models (1)

Updated 24 Oct 2026 · 10:40 America/New_York · Forecasts stay unchanged. Grading uses current corrected regulation results; extra time and penalties are excluded. Rounded probability vectors are normalized for scoring; log loss uses natural logs with a 1e-15 floor.

The evidence

Versions for this fixture

View all forecasts →

Times shown in America/New_York. The highlighted probability is the published pick; the underlined outcome is what happened after 90 minutes.

Versions for this fixture

Get the full match analysis

Share this page