Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Eileen vs Jeffry
Matches counted640
Win rate53.3%
Widest swing11.2 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 |
|---|---|---|---|---|---|
| Single wall | 64.5% | +11.2 | 0.037 | 76 · | |
| Low fence | 59.7% | +6.4 | 0.245 | 72 · | |
| Breakable full fence | 55.4% | +2.1 | 0.697 | 74 · | |
| Breakable half fence | 53.7% | +0.5 | 0.938 | 67 · | |
| Fence and open | 53.6% | +0.3 | 0.975 | 28 · | |
| Rectangle | 52.6% | -0.7 | 0.918 | 57 · | |
| Open | 50.9% | -2.3 | 0.722 | 53 · | |
| Full fence | 49.1% | -4.2 | 0.515 | 55 · | |
| Octagon | 46.6% | -6.7 | 0.222 | 73 · | |
| Half fence | 44.8% | -8.4 | 0.176 | 58 · |
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 8.66 on 9 df, p 0.470
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 49.1%55 | -6.30.477 | +4.30.650 | -4.60.610 | -10.60.233 | -15.40.078 | -4.50.699 | -1.90.847 | -3.50.708 | +2.50.778 |
| Breakable full fence | +6.30.477 | 55.4%74 | +10.60.228 | +1.70.842 | -4.30.598 | -9.10.257 | +1.80.868 | +4.50.619 | +2.80.752 | +8.80.284 |
| Half fence | -4.30.650 | -10.60.228 | 44.8%58 | -8.90.321 | -14.90.091 | -19.60.023 | -8.70.447 | -6.10.519 | -7.80.403 | -1.80.842 |
| Breakable half fence | +4.60.610 | -1.70.842 | +8.90.321 | 53.7%67 | -6.00.476 | -10.70.192 | +0.20.989 | +2.80.761 | +1.10.903 | +7.20.398 |
| Low fence | +10.60.233 | +4.30.598 | +14.90.091 | +6.00.476 | 59.7%72 | -4.80.551 | +6.20.576 | +8.80.328 | +7.10.420 | +13.10.113 |
| Single wall | +15.40.078 | +9.10.257 | +19.60.023 | +10.70.192 | +4.80.551 | 64.5%76 | +10.90.311 | +13.50.124 | +11.80.169 | +17.90.028 |
| Fence and open | +4.50.699 | -1.80.868 | +8.70.447 | -0.20.989 | -6.20.576 | -10.90.311 | 53.6%28 | +2.60.822 | +0.90.935 | +7.00.529 |
| Open | +1.90.847 | -4.50.619 | +6.10.519 | -2.80.761 | -8.80.328 | -13.50.124 | -2.60.822 | 50.9%53 | -1.70.859 | +4.40.628 |
| Rectangle | +3.50.708 | -2.80.752 | +7.80.403 | -1.10.903 | -7.10.420 | -11.80.169 | -0.90.935 | +1.70.859 | 52.6%57 | +6.00.493 |
| Octagon | -2.50.778 | -8.80.284 | +1.80.842 | -7.20.398 | -13.10.113 | -17.90.028 | -7.00.529 | -4.40.628 | -6.00.493 | 46.6%73 |
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 counted542
Win rate51.7%
Widest swing-11.7 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 |
|---|---|---|---|---|---|
| Single wall | 61.4% | +9.8 | 0.080 | 70 · | |
| Low fence | 57.6% | +5.9 | 0.305 | 66 · | |
| Breakable half fence | 53.7% | +2.0 | 0.752 | 54 · | |
| Breakable full fence | 53.3% | +1.7 | 0.783 | 60 · | |
| Rectangle | 52.0% | +0.3 | 0.960 | 50 · | |
| Fence and open | 50.0% | -1.7 | 0.862 | 26 · | |
| Octagon | 47.7% | -4.0 | 0.495 | 65 · | |
| Open | 47.4% | -4.3 | 0.583 | 38 · | |
| Full fence | 46.7% | -5.0 | 0.484 | 45 · | |
| Half fence | 40.0% | -11.7 | 0.102 | 45 · |
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 7.37 on 9 df, p 0.598
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 46.7%45 | -6.70.499 | +6.70.523 | -7.00.486 | -10.90.258 | -14.80.120 | -3.30.786 | -0.70.949 | -5.30.604 | -1.00.916 |
| Breakable full fence | +6.70.499 | 53.3%60 | +13.30.176 | -0.40.968 | -4.20.632 | -8.10.352 | +3.30.776 | +6.00.565 | +1.30.889 | +5.60.529 |
| Half fence | -6.70.523 | -13.30.176 | 40.0%45 | -13.70.174 | -17.60.069 | -21.40.025 | -10.00.413 | -7.40.500 | -12.00.242 | -7.70.425 |
| Breakable half fence | +7.00.486 | +0.40.968 | +13.70.174 | 53.7%54 | -3.90.671 | -7.70.387 | +3.70.756 | +6.30.549 | +1.70.862 | +6.00.514 |
| Low fence | +10.90.258 | +4.20.632 | +17.60.069 | +3.90.671 | 57.6%66 | -3.90.647 | +7.60.510 | +10.20.315 | +5.60.550 | +9.90.257 |
| Single wall | +14.80.120 | +8.10.352 | +21.40.025 | +7.70.387 | +3.90.647 | 61.4%70 | +11.40.313 | +14.10.159 | +9.40.303 | +13.70.109 |
| Fence and open | +3.30.786 | -3.30.776 | +10.00.413 | -3.70.756 | -7.60.510 | -11.40.313 | 50.0%26 | +2.60.836 | -2.00.869 | +2.30.842 |
| Open | +0.70.949 | -6.00.565 | +7.40.500 | -6.30.549 | -10.20.315 | -14.10.159 | -2.60.836 | 47.4%38 | -4.60.667 | -0.30.975 |
| Rectangle | +5.30.604 | -1.30.889 | +12.00.242 | -1.70.862 | -5.60.550 | -9.40.303 | +2.00.869 | +4.60.667 | 52.0%50 | +4.30.647 |
| Octagon | +1.00.916 | -5.60.529 | +7.70.425 | -6.00.514 | -9.90.257 | -13.70.109 | -2.30.842 | +0.30.975 | -4.30.647 | 47.7%65 |
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 counted98
Win rate62.2%
Widest swing37.8 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 |
|---|---|---|---|---|---|
| Fence and open | 100.0% | +37.8 | 0.266 | 2 · | |
| Single wall | 100.0% | +37.8 | 0.049 | 6 · | |
| Low fence | 83.3% | +21.1 | 0.271 | 6 · | |
| Breakable full fence | 64.3% | +2.0 | 0.865 | 14 · | |
| Half fence | 61.5% | -0.7 | 0.955 | 13 · | |
| Full fence | 60.0% | -2.2 | 0.877 | 10 · | |
| Open | 60.0% | -2.2 | 0.845 | 15 · | |
| Rectangle | 57.1% | -5.1 | 0.773 | 7 · | |
| Breakable half fence | 53.9% | -8.4 | 0.502 | 13 · | |
| Octagon | 37.5% | -24.7 | 0.132 | 8 · |
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 8.66 on 9 df, p 0.469
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 60.0%10 | -4.30.831 | -1.50.940 | +6.20.768 | -23.30.330 | -40.00.074 | -40.00.273 | +0.01.000 | +2.90.906 | +22.50.343 |
| Breakable full fence | +4.30.831 | 64.3%14 | +2.80.883 | +10.40.581 | -19.00.394 | -35.70.091 | -35.70.308 | +4.30.812 | +7.20.751 | +26.80.225 |
| Half fence | +1.50.940 | -2.80.883 | 61.5%13 | +7.70.691 | -21.80.342 | -38.50.077 | -38.50.283 | +1.50.934 | +4.40.848 | +24.00.284 |
| Breakable half fence | -6.20.768 | -10.40.581 | -7.70.691 | 53.9%13 | -29.50.216 | -46.10.044 | -46.10.215 | -6.20.743 | -3.30.888 | +16.40.466 |
| Low fence | +23.30.330 | +19.00.394 | +21.80.342 | +29.50.216 | 83.3%6 | -16.70.296 | -16.70.537 | +23.30.306 | +26.20.308 | +45.80.086 |
| Single wall | +40.00.074 | +35.70.091 | +38.50.077 | +46.10.044 | +16.70.296 | 100.0%6 | +0.01.000 | +40.00.067 | +42.90.067 | +62.50.016 |
| Fence and open | +40.00.273 | +35.70.308 | +38.50.283 | +46.10.215 | +16.70.537 | -0.01.000 | 100.0%2 | +40.00.266 | +42.90.257 | +62.50.114 |
| Open | -0.01.000 | -4.30.812 | -1.50.934 | +6.20.743 | -23.30.306 | -40.00.067 | -40.00.266 | 60.0%15 | +2.90.899 | +22.50.304 |
| Rectangle | -2.90.906 | -7.20.751 | -4.40.848 | +3.30.888 | -26.20.308 | -42.90.067 | -42.90.257 | -2.90.899 | 57.1%7 | +19.60.447 |
| Octagon | -22.50.343 | -26.80.225 | -24.00.284 | -16.40.466 | -45.80.086 | -62.50.016 | -62.50.114 | -22.50.304 | -19.60.447 | 37.5%8 |
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.