RadarLiga 1 · Surprises against the model
2024-25 ↺ — 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? →
300 matches with an estimate out of 315 played (teams with fewer than 8 matches in the model's window have no estimate).
The biggest upsets 2024-25 ↺
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 72% · X 18% · 2 9.5% · the actual result had 9.5% (≈ 1 in 10.52)
- ↺model: 1 69% · X 19% · 2 12.0% · the actual result had 12.0% (≈ 1 in 8.33)
- ↺model: 1 68% · X 20% · 2 12.0% · the actual result had 12.0% (≈ 1 in 8.31)
- ↺FCSB 0–1 Politehnica Iasimodel: 1 67% · X 21% · 2 12.7% · the actual result had 12.7% (≈ 1 in 7.88)
- ↺model: 1 63% · X 24% · 2 13.2% · the actual result had 13.2% (≈ 1 in 7.60)
- ↺model: 1 64% · X 22% · 2 14.0% · the actual result had 14.0% (≈ 1 in 7.12)
- ↺model: 1 58% · X 25% · 2 17.4% · the actual result had 17.4% (≈ 1 in 5.74)
- ↺model: 1 52% · X 30% · 2 17.6% · the actual result had 17.6% (≈ 1 in 5.68)
- ↺model: 1 58% · X 24% · 2 18.1% · the actual result had 18.1% (≈ 1 in 5.52)
- ↺model: 1 54% · X 27% · 2 19.0% · the actual result had 19.0% (≈ 1 in 5.25)
- ↺model: 1 19.8% · X 21% · 2 59% · the actual result had 19.8% (≈ 1 in 5.06)
- ↺model: 1 55% · X 25% · 2 20.2% · the actual result had 20.2% (≈ 1 in 4.96)
- ↺model: 1 67% · X 20.5% · 2 13% · the actual result had 20.5% (≈ 1 in 4.88)
- ↺model: 1 67% · X 20.6% · 2 13% · the actual result had 20.6% (≈ 1 in 4.86)
- ↺model: 1 53% · X 26% · 2 20.6% · the actual result had 20.6% (≈ 1 in 4.85)
- ↺model: 1 51% · X 27% · 2 21.0% · the actual result had 21.0% (≈ 1 in 4.75)
- ↺model: 1 50% · X 29% · 2 21.1% · the actual result had 21.1% (≈ 1 in 4.74)
- ↺model: 1 63% · X 21.5% · 2 15% · the actual result had 21.5% (≈ 1 in 4.66)
- ↺model: 1 47% · X 31% · 2 21.6% · the actual result had 21.6% (≈ 1 in 4.62)
- ↺model: 1 49% · X 29% · 2 21.8% · the actual result had 21.8% (≈ 1 in 4.59)
How often low-chance results happen n = 300
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% | 5 | 1 | 20.0%95%: 4–62% | 8.7% |
| 10% – 20% | 86 | 10 | 11.6%95%: 6–20% | 16.2% |
| 20% – 30% | 355 | 115 | 32.4%95%: 28–37% | 26.1% |
Results under 20% that came: 11; expected on average 14.3 (if the model is right, between 8 and 21, 95%).
Teams and upsets 2024-25 ↺
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 |
|---|---|---|---|---|---|
| Uta Arad | 38 | 2 | 1.3 | 0 | 0.1 |
| Oţelul | 39 | 1 | 0.5 | 1 | 0.8 |
| Universitatea Cluj | 39 | 1 | 0.8 | 1 | 0.7 |
| Universitatea Craiova | 39 | 0 | 0.0 | 0 | 1.4 |
| FC Botosani | 39 | 2 | 2.2 | 0 | 0.0 |
| Unirea Slobozia | 31 | 1 | 1.3 | 0 | 0.0 |
| SCM Gloria Buzău | 31 | 3 | 3.3 | 0 | 0.0 |
| AFC Hermannstadt | 38 | 0 | 0.4 | 1 | 0.8 |
| FCSB | 39 | 0 | 0.4 | 2 | 1.9 |
| Sepsi OSK Sfantu Gheorghe | 37 | 0 | 0.4 | 1 | 1.2 |
| Rapid | 39 | 0 | 0.4 | 0 | 1.2 |
| Farul Constanta | 38 | 0 | 0.5 | 3 | 1.6 |
| Politehnica Iasi | 38 | 1 | 1.8 | 0 | 0.0 |
| Petrolul Ploiesti | 37 | 0 | 0.9 | 0 | 0.2 |
| CFR 1907 Cluj | 39 | 0 | 0.9 | 2 | 1.8 |
| Dinamo Bucuresti | 39 | 0 | 1.9 | 0 | 0.0 |
This league's current season is not covered by the free source, so there are no estimates frozen in real time here.
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, 08:20 UTC