Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Aoi vs Eileen
Matches counted573
Win rate47.1%
Widest swing13.3 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 | 60.4% | +13.3 | 0.042 | 53 · | |
| Fence and open | 58.6% | +11.5 | 0.203 | 29 · | |
| Octagon | 56.4% | +9.3 | 0.077 | 78 · | |
| Rectangle | 51.0% | +3.9 | 0.567 | 49 · | |
| Full fence | 47.1% | -0.1 | 0.993 | 51 · | |
| Half fence | 41.9% | -5.2 | 0.386 | 62 · | |
| Breakable half fence | 40.4% | -6.7 | 0.337 | 47 · | |
| Low fence | 40.0% | -7.1 | 0.266 | 55 · | |
| Breakable full fence | 37.3% | -9.8 | 0.087 | 67 · | |
| Single wall | 34.9% | -12.2 | 0.095 | 43 · |
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 16.05 on 9 df, p 0.066
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 47.1%51 | +9.80.287 | +5.10.585 | +6.60.509 | +7.10.464 | +12.20.233 | -11.60.320 | -13.30.173 | -4.00.692 | -9.30.298 |
| Breakable full fence | -9.80.287 | 37.3%67 | -4.60.592 | -3.10.737 | -2.70.762 | +2.40.796 | -21.30.053 | -23.10.012 | -13.70.141 | -19.10.022 |
| Half fence | -5.10.585 | +4.60.592 | 41.9%62 | +1.50.874 | +1.90.832 | +7.10.466 | -16.70.137 | -18.40.049 | -9.10.340 | -14.50.089 |
| Breakable half fence | -6.60.509 | +3.10.737 | -1.50.874 | 40.4%47 | +0.40.965 | +5.50.588 | -18.20.123 | -19.90.046 | -10.60.298 | -16.00.083 |
| Low fence | -7.10.464 | +2.70.762 | -1.90.832 | -0.40.965 | 40.0%55 | +5.10.604 | -18.60.104 | -20.40.034 | -11.00.260 | -16.40.062 |
| Single wall | -12.20.233 | -2.40.796 | -7.10.466 | -5.50.588 | -5.10.604 | 34.9%43 | -23.70.047 | -25.50.013 | -16.10.119 | -21.50.023 |
| Fence and open | +11.60.320 | +21.30.053 | +16.70.137 | +18.20.123 | +18.60.104 | +23.70.047 | 58.6%29 | -1.80.877 | +7.60.515 | +2.20.837 |
| Open | +13.30.173 | +23.10.012 | +18.40.049 | +19.90.046 | +20.40.034 | +25.50.013 | +1.80.877 | 60.4%53 | +9.40.342 | +4.00.652 |
| Rectangle | +4.00.692 | +13.70.141 | +9.10.340 | +10.60.298 | +11.00.260 | +16.10.119 | -7.60.515 | -9.40.342 | 51.0%49 | -5.40.553 |
| Octagon | +9.30.298 | +19.10.022 | +14.50.089 | +16.00.083 | +16.40.062 | +21.50.023 | -2.20.837 | -4.00.652 | +5.40.553 | 56.4%78 |
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 counted483
Win rate46.2%
Widest swing15.5 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 |
|---|---|---|---|---|---|
| Open | 61.7% | +15.5 | 0.025 | 47 · | |
| Fence and open | 57.7% | +11.5 | 0.226 | 26 · | |
| Octagon | 56.5% | +10.3 | 0.062 | 69 · | |
| Full fence | 48.9% | +2.8 | 0.689 | 47 · | |
| Rectangle | 47.2% | +1.1 | 0.895 | 36 · | |
| Breakable half fence | 40.0% | -6.2 | 0.447 | 35 · | |
| Half fence | 38.6% | -7.5 | 0.293 | 44 · | |
| Breakable full fence | 36.9% | -9.2 | 0.108 | 65 · | |
| Low fence | 36.2% | -10.0 | 0.148 | 47 · | |
| Single wall | 36.1% | -10.1 | 0.208 | 36 · |
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 16.22 on 9 df, p 0.062
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 48.9%47 | +12.00.204 | +10.30.323 | +8.90.421 | +12.80.211 | +12.80.243 | -8.80.473 | -12.80.213 | +1.70.877 | -7.60.421 |
| Breakable full fence | -12.00.204 | 36.9%65 | -1.70.856 | -3.10.762 | +0.80.935 | +0.80.935 | -20.80.071 | -24.80.010 | -10.30.313 | -19.60.023 |
| Half fence | -10.30.323 | +1.70.856 | 38.6%44 | -1.40.902 | +2.50.808 | +2.50.816 | -19.10.122 | -23.10.028 | -8.60.440 | -17.90.064 |
| Breakable half fence | -8.90.421 | +3.10.762 | +1.40.902 | 40.0%35 | +3.80.724 | +3.90.736 | -17.70.171 | -21.70.052 | -7.20.540 | -16.50.111 |
| Low fence | -12.80.211 | -0.80.935 | -2.50.808 | -3.80.724 | 36.2%47 | +0.10.996 | -21.50.076 | -25.50.013 | -11.10.310 | -20.40.031 |
| Single wall | -12.80.243 | -0.80.935 | -2.50.816 | -3.90.736 | -0.10.996 | 36.1%36 | -21.60.092 | -25.60.021 | -11.10.339 | -20.40.047 |
| Fence and open | +8.80.473 | +20.80.071 | +19.10.122 | +17.70.171 | +21.50.076 | +21.60.092 | 57.7%26 | -4.00.737 | +10.50.416 | +1.20.918 |
| Open | +12.80.213 | +24.80.010 | +23.10.028 | +21.70.052 | +25.50.013 | +25.60.021 | +4.00.737 | 61.7%47 | +14.50.188 | +5.20.578 |
| Rectangle | -1.70.877 | +10.30.313 | +8.60.440 | +7.20.540 | +11.10.310 | +11.10.339 | -10.50.416 | -14.50.188 | 47.2%36 | -9.30.365 |
| Octagon | +7.60.421 | +19.60.023 | +17.90.064 | +16.50.111 | +20.40.031 | +20.40.047 | -1.20.918 | -5.20.578 | +9.30.365 | 56.5%69 |
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 counted90
Win rate52.2%
Widest swing-27.2 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 |
|---|---|---|---|---|---|
| Fence and open | 66.7% | +14.4 | 0.610 | 3 · | |
| Low fence | 62.5% | +10.3 | 0.542 | 8 · | |
| Rectangle | 61.5% | +9.3 | 0.467 | 13 · | |
| Octagon | 55.6% | +3.3 | 0.833 | 9 · | |
| Breakable full fence | 50.0% | -2.2 | 0.949 | 2 · | |
| Half fence | 50.0% | -2.2 | 0.833 | 18 · | |
| Open | 50.0% | -2.2 | 0.910 | 6 · | |
| Breakable half fence | 41.7% | -10.6 | 0.432 | 12 · | |
| Single wall | 28.6% | -23.6 | 0.192 | 7 · | |
| Full fence | 25.0% | -27.2 | 0.265 | 4 · |
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 4.26 on 9 df, p 0.894
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 25.0%4 | -25.00.540 | -25.00.364 | -16.70.551 | -37.50.221 | -3.60.898 | -41.70.270 | -25.00.429 | -36.50.200 | -30.60.308 |
| Breakable full fence | +25.00.540 | 50.0%2 | +0.01.000 | +8.30.825 | -12.50.747 | +21.40.571 | -16.70.709 | +0.01.000 | -11.50.756 | -5.60.887 |
| Half fence | +25.00.364 | -0.01.000 | 50.0%18 | +8.30.654 | -12.50.555 | +21.40.332 | -16.70.593 | +0.01.000 | -11.50.524 | -5.60.785 |
| Breakable half fence | +16.70.551 | -8.30.825 | -8.30.654 | 41.7%12 | -20.80.361 | +13.10.568 | -25.00.438 | -8.30.737 | -19.90.320 | -13.90.528 |
| Low fence | +37.50.221 | +12.50.747 | +12.50.555 | +20.80.361 | 62.5%8 | +33.90.189 | -4.20.898 | +12.50.640 | +1.00.965 | +6.90.772 |
| Single wall | +3.60.898 | -21.40.571 | -21.40.332 | -13.10.568 | -33.90.189 | 28.6%7 | -38.10.260 | -21.40.429 | -33.00.160 | -27.00.280 |
| Fence and open | +41.70.270 | +16.70.709 | +16.70.593 | +25.00.438 | +4.20.898 | +38.10.260 | 66.7%3 | +16.70.635 | +5.10.869 | +11.10.735 |
| Open | +25.00.429 | -0.01.000 | -0.01.000 | +8.30.737 | -12.50.640 | +21.40.429 | -16.70.635 | 50.0%6 | -11.50.636 | -5.60.833 |
| Rectangle | +36.50.200 | +11.50.756 | +11.50.524 | +19.90.320 | -1.00.965 | +33.00.160 | -5.10.869 | +11.50.636 | 61.5%13 | +6.00.779 |
| Octagon | +30.60.308 | +5.60.887 | +5.60.785 | +13.90.528 | -6.90.772 | +27.00.280 | -11.10.735 | +5.60.833 | -6.00.779 | 55.6%9 |
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.