RadarSerie A · Surprises against the model
2025-26 ↺ — reconstructed walk-forward estimates: each one calculated only from earlier matches and frozen on match day at 00:00 UTC (the site did not exist then). All leagues → How good is the model? →
364 matches with an estimate out of 380 played (teams with fewer than 8 matches in the model's window have no estimate).
The biggest upsets 2025-26 ↺
The matches in which the result happened that the model gave the smallest chance before kick-off. Example: if the model gave the away win 5% and the away side won, the match is near the top of the list. A 5% chance happens, on average, once every 20 matches.
- ↺model: 1 80% · X 15% · 2 5.8% · the actual result had 5.8% (≈ 1 in 17.25)
- ↺model: 1 76% · X 16% · 2 8.2% · the actual result had 8.2% (≈ 1 in 12.17)
- ↺FC Internazionale Milano 1–1 Hellas Verona FCmodel: 1 86% · X 10.6% · 2 4% · the actual result had 10.6% (≈ 1 in 9.48)
- ↺model: 1 64% · X 24% · 2 12.1% · the actual result had 12.1% (≈ 1 in 8.26)
- ↺Hellas Verona FC 3–1 Atalanta BCmodel: 1 12.2% · X 21% · 2 66% · the actual result had 12.2% (≈ 1 in 8.22)
- ↺Bologna FC 1909 1–2 Hellas Verona FCmodel: 1 66% · X 22% · 2 12.5% · the actual result had 12.5% (≈ 1 in 8.00)
- ↺model: 1 65% · X 22% · 2 13.1% · the actual result had 13.1% (≈ 1 in 7.63)
- ↺model: 1 64% · X 21% · 2 14.5% · the actual result had 14.5% (≈ 1 in 6.91)
- ↺model: 1 63% · X 22% · 2 15.0% · the actual result had 15.0% (≈ 1 in 6.68)
- ↺model: 1 15.2% · X 23% · 2 62% · the actual result had 15.2% (≈ 1 in 6.59)
- ↺ACF Fiorentina 1–2 Hellas Verona FCmodel: 1 61% · X 24% · 2 15.6% · the actual result had 15.6% (≈ 1 in 6.40)
- ↺model: 1 16.0% · X 22% · 2 61% · the actual result had 16.0% (≈ 1 in 6.25)
- ↺model: 1 16.1% · X 21% · 2 63% · the actual result had 16.1% (≈ 1 in 6.21)
- ↺model: 1 16.3% · X 25% · 2 59% · the actual result had 16.3% (≈ 1 in 6.15)
- ↺model: 1 54% · X 29% · 2 16.6% · the actual result had 16.6% (≈ 1 in 6.02)
- ↺model: 1 58% · X 25% · 2 17.0% · the actual result had 17.0% (≈ 1 in 5.89)
- ↺model: 1 17.2% · X 26% · 2 57% · the actual result had 17.2% (≈ 1 in 5.81)
- ↺model: 1 17.6% · X 22% · 2 60% · the actual result had 17.6% (≈ 1 in 5.67)
- ↺model: 1 18.0% · X 27% · 2 55% · the actual result had 18.0% (≈ 1 in 5.55)
- ↺model: 1 59% · X 23% · 2 18.1% · the actual result had 18.1% (≈ 1 in 5.53)
How often low-chance results happen n = 364
All the possible results (home win, draw, away win) the model gave a small chance to, grouped into bands. For each band: how often they happened, next to what the model estimated on average. A well-calibrated model has the two numbers close together.
| the model's chance | results | happened | actual | estimated on average |
|---|---|---|---|---|
| 0% – 10% | 28 | 2 | 7.1%95%: 2–23% | 7.7% |
| 10% – 20% | 151 | 25 | 16.6%95%: 11–23% | 15.7% |
| 20% – 30% | 408 | 103 | 25.2%95%: 21–30% | 25.8% |
Results under 20% that came: 27; expected on average 25.9 (if the model is right, between 17 and 35, 95%).
Teams and upsets 2025-26 ↺
For each team: the results under 20% that went its way (a win or a draw) and against it (a defeat), next to how many were expected on average. “Expected” = the sum of those results' chances in its matches.
| Team | matches | in favour: actual | expected | against: actual | expected |
|---|---|---|---|---|---|
| Udinese Calcio | 36 | 5 | 2.3 | 0 | 0.0 |
| Cagliari Calcio | 38 | 5 | 2.9 | 0 | 0.0 |
| Hellas Verona FC | 36 | 5 | 3.3 | 0 | 0.0 |
| US Sassuolo Calcio | 37 | 4 | 2.5 | 0 | 0.0 |
| AC Milan | 36 | 2 | 0.7 | 3 | 2.0 |
| Juventus FC | 38 | 1 | 0.4 | 2 | 2.8 |
| ACF Fiorentina | 37 | 1 | 0.5 | 3 | 1.0 |
| Torino FC | 38 | 2 | 1.6 | 0 | 0.0 |
| SSC Napoli | 37 | 0 | 0.2 | 1 | 2.2 |
| SS Lazio | 38 | 0 | 0.3 | 1 | 1.4 |
| Bologna FC 1909 | 37 | 0 | 0.4 | 3 | 2.0 |
| AS Roma | 37 | 0 | 0.4 | 3 | 2.3 |
| FC Internazionale Milano | 37 | 2 | 2.5 | 2 | 3.2 |
| US Cremonese | 30 | 1 | 1.5 | 0 | 0.2 |
| Como 1907 | 37 | 0 | 0.5 | 0 | 1.7 |
| Parma Calcio 1913 | 37 | 2 | 2.6 | 0 | 0.2 |
| Atalanta BC | 36 | 0 | 0.7 | 5 | 2.2 |
| Genoa CFC | 38 | 0 | 1.4 | 0 | 0.2 |
| AC Pisa 1909 | 30 | 0 | 2.4 | 0 | 0.0 |
| US Lecce | 38 | 1 | 3.4 | 0 | 0.0 |
This season · estimates frozen in real time ❄
The matches of the current season played after the model's estimate was frozen, within the last hour before kick-off, in which a result under 20% came.
23 matches played with a frozen estimate ❄; in 1 of them a result under 20% came.
- ❄Venezia FC 1–0 SSC Napolimodel: 1 10.4% · X 20% · 2 69% · the actual result had 10.4% (≈ 1 in 9.60)
How to read it
How to read the figures on this page and what they do not say.
- A match's upset = the chance the model gave, before kick-off, to the result that happened (home win, draw or away win). The smaller it is, the less the model expected the result.
- A result with a 20% chance happens, on average, once every 5 matches. Upsets are normal: the right question is whether they come as often as the model says — the “How often” table answers it.
- Estimates marked ↺ are reconstructed: calculated only from earlier matches, but the site did not publish them at the time. Those marked ❄ were frozen and published within the last hour before kick-off.
- The figures say what happened against the estimate, not why.
Updated: 25 Oct 2026, 07:20 UTC