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.

479graded matches

0.6008Multiclass Brier (0–2)

1.0022Log loss

500 considered · 0 awaiting results · 21 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%	6.0%	4.7%	43
10–20%	16.4%	17.1%	164
20–30%	25.1%	26.1%	582
30–40%	34.9%	36.1%	244
40–50%	44.8%	40.5%	190
50–60%	55.0%	55.2%	116
60–70%	64.3%	63.8%	58
70–80%	75.8%	70.8%	24
80–90%	82.3%	80.0%	10
90–100%	95.0%	100.0%	6

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 (478) · Earlier models (1)

Updated 25 Oct 2026 · 08:01 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