Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Aoi vs Jean
Matches counted1,525
Win rate51.3%
Widest swing-7.1 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 |
|---|---|---|---|---|---|
| Rectangle | 57.0% | +5.8 | 0.128 | 156 | |
| Breakable full fence | 56.6% | +5.3 | 0.168 | 152 | |
| Open | 53.7% | +2.4 | 0.514 | 162 | |
| Octagon | 53.6% | +2.3 | 0.588 | 125 | |
| Full fence | 53.2% | +1.9 | 0.616 | 158 | |
| Single wall | 50.8% | -0.5 | 0.897 | 134 | |
| Fence and open | 50.0% | -1.3 | 0.827 | 70 · | |
| Breakable half fence | 49.1% | -2.2 | 0.554 | 159 | |
| Low fence | 46.1% | -5.2 | 0.140 | 180 | |
| Half fence | 44.1% | -7.1 | 0.071 | 145 |
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 9.91 on 9 df, p 0.358
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 53.2%158 | -3.40.546 | +9.00.116 | +4.10.464 | +7.00.196 | +2.40.680 | +3.20.659 | -0.50.923 | -3.90.489 | -0.40.942 |
| Breakable full fence | +3.40.546 | 56.6%152 | +12.40.032 | +7.50.184 | +10.50.057 | +5.80.323 | +6.60.360 | +2.90.609 | -0.50.933 | +3.00.620 |
| Half fence | -9.00.116 | -12.40.032 | 44.1%145 | -4.90.391 | -2.00.722 | -6.60.269 | -5.90.419 | -9.60.094 | -12.90.025 | -9.50.121 |
| Breakable half fence | -4.10.464 | -7.50.184 | +4.90.391 | 49.1%159 | +3.00.588 | -1.70.773 | -0.90.895 | -4.60.405 | -8.00.155 | -4.50.447 |
| Low fence | -7.00.196 | -10.50.057 | +2.00.722 | -3.00.588 | 46.1%180 | -4.60.416 | -3.90.580 | -7.60.161 | -10.90.045 | -7.50.198 |
| Single wall | -2.40.680 | -5.80.323 | +6.60.269 | +1.70.773 | +4.60.416 | 50.8%134 | +0.80.919 | -3.00.612 | -6.30.283 | -2.90.646 |
| Fence and open | -3.20.659 | -6.60.360 | +5.90.419 | +0.90.895 | +3.90.580 | -0.80.919 | 50.0%70 | -3.70.604 | -7.00.325 | -3.60.629 |
| Open | +0.50.923 | -2.90.609 | +9.60.094 | +4.60.405 | +7.60.161 | +3.00.612 | +3.70.604 | 53.7%162 | -3.40.548 | +0.10.986 |
| Rectangle | +3.90.489 | +0.50.933 | +12.90.025 | +8.00.155 | +10.90.045 | +6.30.283 | +7.00.325 | +3.40.548 | 57.0%156 | +3.50.563 |
| Octagon | +0.40.942 | -3.00.620 | +9.50.121 | +4.50.447 | +7.50.198 | +2.90.646 | +3.60.629 | -0.10.986 | -3.50.563 | 53.6%125 |
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 counted1,469
Win rate50.9%
Widest swing-7.8 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 |
|---|---|---|---|---|---|
| Breakable full fence | 57.1% | +6.2 | 0.112 | 147 | |
| Rectangle | 56.6% | +5.7 | 0.140 | 152 | |
| Full fence | 54.0% | +3.1 | 0.426 | 150 | |
| Octagon | 53.6% | +2.7 | 0.531 | 125 | |
| Open | 52.2% | +1.3 | 0.728 | 157 | |
| Breakable half fence | 50.0% | -0.9 | 0.812 | 150 | |
| Fence and open | 50.0% | -0.9 | 0.875 | 70 · | |
| Single wall | 48.8% | -2.1 | 0.620 | 125 | |
| Low fence | 45.4% | -5.5 | 0.121 | 174 | |
| Half fence | 43.2% | -7.8 | 0.055 | 139 |
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 11.01 on 9 df, p 0.275
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 54.0%150 | -3.10.586 | +10.80.066 | +4.00.488 | +8.60.123 | +5.20.390 | +4.00.580 | +1.80.756 | -2.60.652 | +0.40.947 |
| Breakable full fence | +3.10.586 | 57.1%147 | +14.00.018 | +7.10.217 | +11.70.036 | +8.30.169 | +7.10.323 | +4.90.390 | +0.60.922 | +3.50.558 |
| Half fence | -10.80.066 | -14.00.018 | 43.2%139 | -6.80.245 | -2.20.692 | -5.60.359 | -6.80.349 | -9.10.119 | -13.40.022 | -10.40.090 |
| Breakable half fence | -4.00.488 | -7.10.217 | +6.80.245 | 50.0%150 | +4.60.409 | +1.20.843 | +0.01.000 | -2.20.696 | -6.60.252 | -3.60.552 |
| Low fence | -8.60.123 | -11.70.036 | +2.20.692 | -4.60.409 | 45.4%174 | -3.40.561 | -4.60.515 | -6.80.215 | -11.20.044 | -8.20.162 |
| Single wall | -5.20.390 | -8.30.169 | +5.60.359 | -1.20.843 | +3.40.561 | 48.8%125 | -1.20.872 | -3.40.567 | -7.80.197 | -4.80.448 |
| Fence and open | -4.00.580 | -7.10.323 | +6.80.349 | -0.01.000 | +4.60.515 | +1.20.872 | 50.0%70 | -2.20.756 | -6.60.360 | -3.60.629 |
| Open | -1.80.756 | -4.90.390 | +9.10.119 | +2.20.696 | +6.80.215 | +3.40.567 | +2.20.756 | 52.2%157 | -4.30.443 | -1.40.819 |
| Rectangle | +2.60.652 | -0.60.922 | +13.40.022 | +6.60.252 | +11.20.044 | +7.80.197 | +6.60.360 | +4.30.443 | 56.6%152 | +3.00.620 |
| Octagon | -0.40.947 | -3.50.558 | +10.40.090 | +3.60.552 | +8.20.162 | +4.80.448 | +3.60.629 | +1.40.819 | -3.00.620 | 53.6%125 |
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 counted56
Win rate60.7%
Widest swing39.3 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 |
|---|---|---|---|---|---|
| Open | 100.0% | +39.3 | 0.059 | 5 · | |
| Single wall | 77.8% | +17.1 | 0.253 | 9 · | |
| Rectangle | 75.0% | +14.3 | 0.544 | 4 · | |
| Half fence | 66.7% | +6.0 | 0.752 | 6 · | |
| Low fence | 66.7% | +6.0 | 0.752 | 6 · | |
| Breakable full fence | 40.0% | -20.7 | 0.320 | 5 · | |
| Full fence | 37.5% | -23.2 | 0.146 | 8 · | |
| Breakable half fence | 33.3% | -27.4 | 0.066 | 9 · |
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 10.27 on 7 df, p 0.174
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Open | Rect |
|---|---|---|---|---|---|---|---|---|
| Full fence | 37.5%8 | -2.50.928 | -29.20.280 | +4.20.858 | -29.20.280 | -40.30.092 | -62.50.024 | -37.50.221 |
| Breakable full fence | +2.50.928 | 40.0%5 | -26.70.376 | +6.70.803 | -26.70.376 | -37.80.158 | -60.00.038 | -35.00.294 |
| Half fence | +29.20.280 | +26.70.376 | 66.7%6 | +33.30.205 | +0.01.000 | -11.10.634 | -33.30.154 | -8.30.778 |
| Breakable half fence | -4.20.858 | -6.70.803 | -33.30.205 | 33.3%9 | -33.30.205 | -44.50.058 | -66.70.016 | -41.70.164 |
| Low fence | +29.20.280 | +26.70.376 | -0.01.000 | +33.30.205 | 66.7%6 | -11.10.634 | -33.30.154 | -8.30.778 |
| Single wall | +40.30.092 | +37.80.158 | +11.10.634 | +44.50.058 | +11.10.634 | 77.8%9 | -22.20.255 | +2.80.913 |
| Open | +62.50.024 | +60.00.038 | +33.30.154 | +66.70.016 | +33.30.154 | +22.20.255 | 100.0%5 | +25.00.236 |
| Rectangle | +37.50.221 | +35.00.294 | +8.30.778 | +41.70.164 | +8.30.778 | -2.80.913 | -25.00.236 | 75.0%4 |
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.