Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Eileen vs Shun
Matches counted659
Win rate54.8%
Widest swing14.6 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Eileen's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Open | 69.3% | +14.6 | 0.007 | 75 · | |
| Breakable full fence | 65.0% | +10.2 | 0.095 | 60 · | |
| Full fence | 58.2% | +3.5 | 0.512 | 79 · | |
| Breakable half fence | 55.4% | +0.6 | 0.900 | 83 | |
| Rectangle | 54.4% | -0.3 | 0.947 | 79 · | |
| Fence and open | 50.0% | -4.8 | 0.542 | 38 · | |
| Low fence | 50.0% | -4.8 | 0.510 | 44 · | |
| Single wall | 49.0% | -5.8 | 0.396 | 49 · | |
| Octagon | 46.5% | -8.3 | 0.137 | 71 · | |
| Half fence | 45.8% | -9.0 | 0.145 | 59 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Eileen's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 14.66 on 9 df, p 0.101
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 58.2%79 | -6.80.417 | +12.50.147 | +2.80.719 | +8.20.379 | +9.20.307 | +8.20.402 | -11.10.152 | +3.80.630 | +11.80.150 |
| Breakable full fence | +6.80.417 | 65.0%60 | +19.20.035 | +9.60.250 | +15.00.125 | +16.00.092 | +15.00.141 | -4.30.594 | +10.60.210 | +18.50.034 |
| Half fence | -12.50.147 | -19.20.035 | 45.8%59 | -9.70.256 | -4.20.670 | -3.20.739 | -4.20.683 | -23.60.006 | -8.70.314 | -0.70.935 |
| Breakable half fence | -2.80.719 | -9.60.250 | +9.70.256 | 55.4%83 | +5.40.560 | +6.40.474 | +5.40.579 | -13.90.072 | +1.00.899 | +8.90.268 |
| Low fence | -8.20.379 | -15.00.125 | +4.20.670 | -5.40.560 | 50.0%44 | +1.00.922 | +0.01.000 | -19.30.036 | -4.40.637 | +3.50.713 |
| Single wall | -9.20.307 | -16.00.092 | +3.20.739 | -6.40.474 | -1.00.922 | 49.0%49 | -1.00.925 | -20.40.023 | -5.50.548 | +2.50.787 |
| Fence and open | -8.20.402 | -15.00.141 | +4.20.683 | -5.40.579 | -0.01.000 | +1.00.925 | 50.0%38 | -19.30.045 | -4.40.653 | +3.50.726 |
| Open | +11.10.152 | +4.30.594 | +23.60.006 | +13.90.072 | +19.30.036 | +20.40.023 | +19.30.045 | 69.3%75 | +14.90.057 | +22.90.005 |
| Rectangle | -3.80.630 | -10.60.210 | +8.70.314 | -1.00.899 | +4.40.637 | +5.50.548 | +4.40.653 | -14.90.057 | 54.4%79 | +8.00.331 |
| Octagon | -11.80.150 | -18.50.034 | +0.70.935 | -8.90.268 | -3.50.713 | -2.50.787 | -3.50.726 | -22.90.005 | -8.00.331 | 46.5%71 |
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 counted445
Win rate57.1%
Widest swing11.4 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Eileen's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Open | 68.5% | +11.4 | 0.070 | 54 · | |
| Fence and open | 60.0% | +2.9 | 0.761 | 25 · | |
| Low fence | 60.0% | +2.9 | 0.761 | 25 · | |
| Breakable full fence | 59.5% | +2.4 | 0.737 | 42 · | |
| Breakable half fence | 59.3% | +2.2 | 0.730 | 54 · | |
| Full fence | 57.6% | +0.6 | 0.927 | 59 · | |
| Rectangle | 57.6% | +0.6 | 0.927 | 59 · | |
| Single wall | 51.9% | -5.2 | 0.571 | 27 · | |
| Octagon | 46.0% | -11.1 | 0.093 | 50 · | |
| Half fence | 45.7% | -11.4 | 0.157 | 35 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Eileen's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 7.93 on 9 df, p 0.542
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 57.6%59 | -1.90.849 | +11.90.263 | -1.60.860 | -2.40.840 | +5.80.617 | -2.40.840 | -10.90.231 | +0.01.000 | +11.60.226 |
| Breakable full fence | +1.90.849 | 59.5%42 | +13.80.227 | +0.30.979 | -0.50.969 | +7.70.530 | -0.50.969 | -9.00.361 | +1.90.849 | +13.50.196 |
| Half fence | -11.90.263 | -13.80.227 | 45.7%35 | -13.60.210 | -14.30.275 | -6.10.632 | -14.30.275 | -22.80.032 | -11.90.263 | -0.30.979 |
| Breakable half fence | +1.60.860 | -0.30.979 | +13.60.210 | 59.3%54 | -0.70.950 | +7.40.526 | -0.70.950 | -9.30.317 | +1.60.860 | +13.30.176 |
| Low fence | +2.40.840 | +0.50.969 | +14.30.275 | +0.70.950 | 60.0%25 | +8.20.554 | +0.01.000 | -8.50.458 | +2.40.840 | +14.00.253 |
| Single wall | -5.80.617 | -7.70.530 | +6.10.632 | -7.40.526 | -8.20.554 | 51.9%27 | -8.20.554 | -16.70.143 | -5.80.617 | +5.80.624 |
| Fence and open | +2.40.840 | +0.50.969 | +14.30.275 | +0.70.950 | -0.01.000 | +8.20.554 | 60.0%25 | -8.50.458 | +2.40.840 | +14.00.253 |
| Open | +10.90.231 | +9.00.361 | +22.80.032 | +9.30.317 | +8.50.458 | +16.70.143 | +8.50.458 | 68.5%54 | +10.90.231 | +22.50.020 |
| Rectangle | -0.01.000 | -1.90.849 | +11.90.263 | -1.60.860 | -2.40.840 | +5.80.617 | -2.40.840 | -10.90.231 | 57.6%59 | +11.60.226 |
| Octagon | -11.60.226 | -13.50.196 | +0.30.979 | -13.30.176 | -14.00.253 | -5.80.624 | -14.00.253 | -22.50.020 | -11.60.226 | 46.0%50 |
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 counted214
Win rate50.0%
Widest swing27.8 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Eileen's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Breakable full fence | 77.8% | +27.8 | 0.014 | 18 · | |
| Open | 71.4% | +21.4 | 0.039 | 21 · | |
| Full fence | 60.0% | +10.0 | 0.348 | 20 · | |
| Breakable half fence | 48.3% | -1.7 | 0.842 | 29 · | |
| Octagon | 47.6% | -2.4 | 0.818 | 21 · | |
| Half fence | 45.8% | -4.2 | 0.665 | 24 · | |
| Single wall | 45.5% | -4.5 | 0.653 | 22 · | |
| Rectangle | 45.0% | -5.0 | 0.639 | 20 · | |
| Low fence | 36.8% | -13.2 | 0.229 | 19 · | |
| Fence and open | 30.8% | -19.2 | 0.152 | 13 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Eileen's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 13.97 on 9 df, p 0.123
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 60.0%20 | -17.80.239 | +14.20.349 | +11.70.419 | +23.20.148 | +14.60.346 | +29.20.101 | -11.40.440 | +15.00.342 | +12.40.427 |
| Breakable full fence | +17.80.239 | 77.8%18 | +31.90.037 | +29.50.045 | +40.90.012 | +32.30.038 | +47.00.009 | +6.30.651 | +32.80.039 | +30.20.054 |
| Half fence | -14.20.349 | -31.90.037 | 45.8%24 | -2.50.859 | +9.00.553 | +0.40.979 | +15.10.373 | -25.60.083 | +0.80.956 | -1.80.905 |
| Breakable half fence | -11.70.419 | -29.50.045 | +2.50.859 | 48.3%29 | +11.40.435 | +2.80.842 | +17.50.289 | -23.10.102 | +3.30.821 | +0.70.963 |
| Low fence | -23.20.148 | -40.90.012 | -9.00.553 | -11.40.435 | 36.8%19 | -8.60.577 | +6.10.722 | -34.60.028 | -8.20.605 | -10.80.491 |
| Single wall | -14.60.346 | -32.30.038 | -0.40.979 | -2.80.842 | +8.60.577 | 45.5%22 | +14.70.392 | -26.00.084 | +0.50.976 | -2.20.887 |
| Fence and open | -29.20.101 | -47.00.009 | -15.10.373 | -17.50.289 | -6.10.722 | -14.70.392 | 30.8%13 | -40.70.020 | -14.20.414 | -16.90.332 |
| Open | +11.40.440 | -6.30.651 | +25.60.083 | +23.10.102 | +34.60.028 | +26.00.084 | +40.70.020 | 71.4%21 | +26.40.086 | +23.80.116 |
| Rectangle | -15.00.342 | -32.80.039 | -0.80.956 | -3.30.821 | +8.20.605 | -0.50.976 | +14.20.414 | -26.40.086 | 45.0%20 | -2.60.867 |
| Octagon | -12.40.427 | -30.20.054 | +1.80.905 | -0.70.963 | +10.80.491 | +2.20.887 | +16.90.332 | -23.80.116 | +2.60.867 | 47.6%21 |
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.