Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Aoi vs Kage
Matches counted1,916
Win rate49.3%
Widest swing3.5 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Aoi's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Low fence | 52.8% | +3.5 | 0.279 | 212 | |
| Octagon | 52.7% | +3.4 | 0.334 | 186 | |
| Fence and open | 49.6% | +0.3 | 0.952 | 121 | |
| Breakable half fence | 48.2% | -1.1 | 0.739 | 193 | |
| Full fence | 48.0% | -1.3 | 0.711 | 173 | |
| Open | 47.6% | -1.7 | 0.671 | 149 | |
| Single wall | 47.5% | -1.8 | 0.609 | 181 | |
| Rectangle | 47.3% | -2.0 | 0.547 | 207 | |
| Half fence | 47.3% | -2.1 | 0.497 | 237 | |
| Breakable full fence | 46.9% | -2.4 | 0.522 | 162 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Aoi's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 3.44 on 9 df, p 0.944
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 48.0%173 | +1.10.846 | +0.70.885 | -0.20.968 | -4.80.343 | +0.50.931 | -1.60.786 | +0.30.953 | +0.60.902 | -4.70.372 |
| Breakable full fence | -1.10.846 | 46.9%162 | -0.30.946 | -1.30.811 | -5.90.257 | -0.60.911 | -2.70.656 | -0.70.896 | -0.40.935 | -5.80.283 |
| Half fence | -0.70.885 | +0.30.946 | 47.3%237 | -0.90.848 | -5.60.238 | -0.20.959 | -2.30.676 | -0.40.940 | -0.10.986 | -5.40.268 |
| Breakable half fence | +0.20.968 | +1.30.811 | +0.90.848 | 48.2%193 | -4.60.351 | +0.70.896 | -1.40.809 | +0.50.922 | +0.80.866 | -4.50.381 |
| Low fence | +4.80.343 | +5.90.257 | +5.60.238 | +4.60.351 | 52.8%212 | +5.30.293 | +3.20.569 | +5.20.333 | +5.50.261 | +0.10.977 |
| Single wall | -0.50.931 | +0.60.911 | +0.20.959 | -0.70.896 | -5.30.293 | 47.5%181 | -2.10.724 | -0.10.980 | +0.20.973 | -5.20.322 |
| Fence and open | +1.60.786 | +2.70.656 | +2.30.676 | +1.40.809 | -3.20.569 | +2.10.724 | 49.6%121 | +1.90.752 | +2.20.695 | -3.10.595 |
| Open | -0.30.953 | +0.70.896 | +0.40.940 | -0.50.922 | -5.20.333 | +0.10.980 | -1.90.752 | 47.6%149 | +0.30.954 | -5.00.359 |
| Rectangle | -0.60.902 | +0.40.935 | +0.10.986 | -0.80.866 | -5.50.261 | -0.20.973 | -2.20.695 | -0.30.954 | 47.3%207 | -5.30.290 |
| Octagon | +4.70.372 | +5.80.283 | +5.40.268 | +4.50.381 | -0.10.977 | +5.20.322 | +3.10.595 | +5.00.359 | +5.30.290 | 52.7%186 |
Better on the row's stage — deeper at 5 and 10 pointsBetter on the column's stagep < 0.05 on its ownStill there after correcting for how many were tested· fewer than 80 decided matches on one side of the comparison
How significance is decided
- Each gap is two win rates compared with a pooled two-proportion z test, over decided matches only.
- The 95% interval is Newcombe's hybrid score method, which keeps its shape near 0% and 100% where a symmetric interval does not.
- q is p corrected for how many tests were asked at once, by Benjamini–Hochberg at a 5% false discovery rate. A figure is called real on q, never on p alone.
- Standard errors are widened by a measured design effect, because one player appears in many matches and those matches are not independent of each other.
- Stages are assigned at random, so a gap between them is the stage's own effect and not a difference in who chose to play where.
Matches counted1,713
Win rate49.0%
Widest swing4.8 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Aoi's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Octagon | 53.8% | +4.8 | 0.205 | 160 | |
| Low fence | 53.4% | +4.4 | 0.195 | 193 | |
| Fence and open | 49.1% | +0.1 | 0.987 | 106 | |
| Single wall | 47.4% | -1.5 | 0.686 | 156 | |
| Rectangle | 47.3% | -1.7 | 0.630 | 186 | |
| Half fence | 47.2% | -1.8 | 0.574 | 212 | |
| Breakable half fence | 47.2% | -1.8 | 0.610 | 176 | |
| Open | 47.1% | -1.9 | 0.641 | 136 | |
| Breakable full fence | 45.7% | -3.3 | 0.398 | 151 | |
| Full fence | 45.6% | -3.3 | 0.393 | 149 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Aoi's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 5.14 on 9 df, p 0.822
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 45.6%149 | -0.10.992 | -1.50.774 | -1.50.784 | -7.70.156 | -1.80.753 | -3.40.590 | -1.40.810 | -1.70.760 | -8.10.154 |
| Breakable full fence | +0.10.992 | 45.7%151 | -1.50.781 | -1.50.791 | -7.70.158 | -1.70.760 | -3.40.595 | -1.40.817 | -1.60.767 | -8.10.156 |
| Half fence | +1.50.774 | +1.50.781 | 47.2%212 | +0.00.998 | -6.20.213 | -0.30.960 | -1.90.751 | +0.10.984 | -0.10.977 | -6.60.209 |
| Breakable half fence | +1.50.784 | +1.50.791 | -0.00.998 | 47.2%176 | -6.20.233 | -0.30.960 | -1.90.757 | +0.10.986 | -0.10.977 | -6.60.228 |
| Low fence | +7.70.156 | +7.70.158 | +6.20.213 | +6.20.233 | 53.4%193 | +5.90.270 | +4.30.475 | +6.30.260 | +6.10.238 | -0.40.943 |
| Single wall | +1.80.753 | +1.70.760 | +0.30.960 | +0.30.960 | -5.90.270 | 47.4%156 | -1.60.797 | +0.40.949 | +0.10.982 | -6.30.262 |
| Fence and open | +3.40.590 | +3.40.595 | +1.90.751 | +1.90.757 | -4.30.475 | +1.60.797 | 49.1%106 | +2.00.758 | +1.80.774 | -4.70.453 |
| Open | +1.40.810 | +1.40.817 | -0.10.984 | -0.10.986 | -6.30.260 | -0.40.949 | -2.00.758 | 47.1%136 | -0.20.964 | -6.70.251 |
| Rectangle | +1.70.760 | +1.60.767 | +0.10.977 | +0.10.977 | -6.10.238 | -0.10.982 | -1.80.774 | +0.20.964 | 47.3%186 | -6.40.232 |
| Octagon | +8.10.154 | +8.10.156 | +6.60.209 | +6.60.228 | +0.40.943 | +6.30.262 | +4.70.453 | +6.70.251 | +6.40.232 | 53.8%160 |
Better on the row's stage — deeper at 5 and 10 pointsBetter on the column's stagep < 0.05 on its ownStill there after correcting for how many were tested· fewer than 80 decided matches on one side of the comparison
How significance is decided
- Each gap is two win rates compared with a pooled two-proportion z test, over decided matches only.
- The 95% interval is Newcombe's hybrid score method, which keeps its shape near 0% and 100% where a symmetric interval does not.
- q is p corrected for how many tests were asked at once, by Benjamini–Hochberg at a 5% false discovery rate. A figure is called real on q, never on p alone.
- Standard errors are widened by a measured design effect, because one player appears in many matches and those matches are not independent of each other.
- Stages are assigned at random, so a gap between them is the stage's own effect and not a difference in who chose to play where.
Matches counted203
Win rate52.2%
Widest swing11.4 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Aoi's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Breakable full fence | 63.6% | +11.4 | 0.436 | 11 · | |
| Full fence | 62.5% | +10.3 | 0.283 | 24 · | |
| Breakable half fence | 58.8% | +6.6 | 0.569 | 17 · | |
| Open | 53.9% | +1.6 | 0.903 | 13 · | |
| Fence and open | 53.3% | +1.1 | 0.928 | 15 · | |
| Half fence | 48.0% | -4.2 | 0.652 | 25 · | |
| Single wall | 48.0% | -4.2 | 0.652 | 25 · | |
| Rectangle | 47.6% | -4.6 | 0.656 | 21 · | |
| Low fence | 47.4% | -4.8 | 0.657 | 19 · | |
| Octagon | 46.1% | -6.1 | 0.507 | 26 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Aoi's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 3.00 on 9 df, p 0.964
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 62.5%24 | -1.10.948 | +14.50.308 | +3.70.812 | +15.10.321 | +14.50.308 | +9.20.571 | +8.70.609 | +14.90.316 | +16.40.247 |
| Breakable full fence | +1.10.948 | 63.6%11 | +15.60.387 | +4.80.799 | +16.30.389 | +15.60.387 | +10.30.599 | +9.80.628 | +16.00.388 | +17.50.331 |
| Half fence | -14.50.308 | -15.60.387 | 48.0%25 | -10.80.491 | +0.60.967 | +0.01.000 | -5.30.744 | -5.80.732 | +0.40.979 | +1.90.895 |
| Breakable half fence | -3.70.812 | -4.80.799 | +10.80.491 | 58.8%17 | +11.40.492 | +10.80.491 | +5.50.755 | +5.00.785 | +11.20.492 | +12.70.416 |
| Low fence | -15.10.321 | -16.30.389 | -0.60.967 | -11.40.492 | 47.4%19 | -0.60.967 | -6.00.730 | -6.50.719 | -0.20.987 | +1.20.936 |
| Single wall | -14.50.308 | -15.60.387 | -0.01.000 | -10.80.491 | +0.60.967 | 48.0%25 | -5.30.744 | -5.80.732 | +0.40.979 | +1.90.895 |
| Fence and open | -9.20.571 | -10.30.599 | +5.30.744 | -5.50.755 | +6.00.730 | +5.30.744 | 53.3%15 | -0.50.978 | +5.70.735 | +7.20.658 |
| Open | -8.70.609 | -9.80.628 | +5.80.732 | -5.00.785 | +6.50.719 | +5.80.732 | +0.50.978 | 53.9%13 | +6.20.724 | +7.70.651 |
| Rectangle | -14.90.316 | -16.00.388 | -0.40.979 | -11.20.492 | +0.20.987 | -0.40.979 | -5.70.735 | -6.20.724 | 47.6%21 | +1.50.920 |
| Octagon | -16.40.247 | -17.50.331 | -1.90.895 | -12.70.416 | -1.20.936 | -1.90.895 | -7.20.658 | -7.70.651 | -1.50.920 | 46.1%26 |
Better on the row's stage — deeper at 5 and 10 pointsBetter on the column's stagep < 0.05 on its ownStill there after correcting for how many were tested· fewer than 80 decided matches on one side of the comparison
How significance is decided
- Each gap is two win rates compared with a pooled two-proportion z test, over decided matches only.
- The 95% interval is Newcombe's hybrid score method, which keeps its shape near 0% and 100% where a symmetric interval does not.
- q is p corrected for how many tests were asked at once, by Benjamini–Hochberg at a 5% false discovery rate. A figure is called real on q, never on p alone.
- Standard errors are widened by a measured design effect, because one player appears in many matches and those matches are not independent of each other.
- Stages are assigned at random, so a gap between them is the stage's own effect and not a difference in who chose to play where.