Original probabilities stay unchanged. Results are graded separately. The archive starts when retention was enabled; earlier forecasts are not reconstructed.
The evidence
Latest published forecasts
Unlock the full forecast story
Create your free account to explore timestamped forecasts, results for each market, team probability history and opponent-adjusted form.
Kostenlose Anmeldung. Ohne Karte.
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.
485graded matches
0.5984Multiclass Brier (0–2)
1.0665Log loss
500 considered · 0 awaiting results · 15 excluded: provenance or result could not be verified
Calibration across home, draw and away outcomes
| Probability band | Mean predicted | Observed frequency | Outcome observations |
|---|
| 0–10% | 5.1% | 10.3% | 29 |
|---|
| 10–20% | 16.2% | 10.5% | 105 |
|---|
| 20–30% | 26.5% | 23.2% | 469 |
|---|
| 30–40% | 34.4% | 33.3% | 529 |
|---|
| 40–50% | 44.1% | 51.0% | 204 |
|---|
| 50–60% | 54.5% | 62.3% | 77 |
|---|
| 60–70% | 64.0% | 80.8% | 26 |
|---|
| 70–80% | 74.4% | 80.0% | 15 |
|---|
| 80–90% | 80.9% | 100.0% | 1 |
|---|
| 90–100% | — | — | 0 |
|---|
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: ML_composition_v8:Advanced_joint_form_v73 (425) · ML_composition_v8:Fallback_regulation_v3 (55) · ML_composition_v8:INTL_regulation_v3 (5)
Updated 19 Sep 2026 · 18:20 UTC · 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.