Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Aoi vs Jeffry
Matches counted1,921
Win rate46.3%
Widest swing-9.7 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 | 53.7% | +7.3 | 0.032 | 190 | |
| Octagon | 50.8% | +4.5 | 0.191 | 193 | |
| Single wall | 49.4% | +3.1 | 0.395 | 172 | |
| Full fence | 48.8% | +2.4 | 0.461 | 203 | |
| Breakable full fence | 46.6% | +0.3 | 0.930 | 221 | |
| Breakable half fence | 45.9% | -0.5 | 0.894 | 194 | |
| Half fence | 45.0% | -1.4 | 0.694 | 189 | |
| Fence and open | 41.4% | -4.9 | 0.287 | 111 | |
| Low fence | 40.5% | -5.8 | 0.111 | 168 | |
| Rectangle | 36.6% | -9.7 | 0.006 | 183 |
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 17.30 on 9 df, p 0.044
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 48.8%203 | +2.20.656 | +3.80.452 | +2.90.564 | +8.30.110 | -0.70.900 | +7.30.213 | -4.90.330 | +12.20.016 | -2.00.689 |
| Breakable full fence | -2.20.656 | 46.6%221 | +1.60.741 | +0.70.882 | +6.10.228 | -2.80.580 | +5.20.372 | -7.10.152 | +10.00.043 | -4.20.397 |
| Half fence | -3.80.452 | -1.60.741 | 45.0%189 | -0.90.859 | +4.50.391 | -4.50.398 | +3.50.551 | -8.70.090 | +8.40.101 | -5.80.256 |
| Breakable half fence | -2.90.564 | -0.70.882 | +0.90.859 | 45.9%194 | +5.40.301 | -3.50.498 | +4.40.453 | -7.80.126 | +9.30.068 | -4.90.335 |
| Low fence | -8.30.110 | -6.10.228 | -4.50.391 | -5.40.301 | 40.5%168 | -8.90.098 | -1.00.872 | -13.20.013 | +3.90.457 | -10.30.050 |
| Single wall | +0.70.900 | +2.80.580 | +4.50.398 | +3.50.498 | +8.90.098 | 49.4%172 | +8.00.189 | -4.30.417 | +12.80.015 | -1.40.796 |
| Fence and open | -7.30.213 | -5.20.372 | -3.50.551 | -4.40.453 | +1.00.872 | -8.00.189 | 41.4%111 | -12.20.040 | +4.80.409 | -9.30.117 |
| Open | +4.90.330 | +7.10.152 | +8.70.090 | +7.80.126 | +13.20.013 | +4.30.417 | +12.20.040 | 53.7%190 | +17.1<0.001 | +2.90.569 |
| Rectangle | -12.20.016 | -10.00.043 | -8.40.101 | -9.30.068 | -3.90.457 | -12.80.015 | -4.80.409 | -17.1<0.001 | 36.6%183 | -14.20.006 |
| Octagon | +2.00.689 | +4.20.397 | +5.80.256 | +4.90.335 | +10.30.050 | +1.40.796 | +9.30.117 | -2.90.569 | +14.20.006 | 50.8%193 |
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 counted1,817
Win rate46.0%
Widest swing-9.2 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 |
|---|---|---|---|---|---|
| Open | 53.9% | +7.9 | 0.025 | 180 | |
| Octagon | 49.7% | +3.7 | 0.294 | 179 | |
| Single wall | 48.5% | +2.5 | 0.510 | 163 | |
| Full fence | 48.1% | +2.1 | 0.533 | 189 | |
| Breakable half fence | 46.3% | +0.3 | 0.938 | 188 | |
| Half fence | 45.6% | -0.5 | 0.897 | 180 | |
| Breakable full fence | 45.4% | -0.6 | 0.854 | 207 | |
| Fence and open | 41.1% | -4.9 | 0.296 | 107 | |
| Low fence | 40.9% | -5.1 | 0.174 | 159 | |
| Rectangle | 36.8% | -9.2 | 0.010 | 174 |
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 14.96 on 9 df, p 0.092
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 48.1%189 | +2.70.585 | +2.60.618 | +1.90.716 | +7.30.174 | -0.30.953 | +7.00.244 | -5.70.270 | +11.40.029 | -1.60.763 |
| Breakable full fence | -2.70.585 | 45.4%207 | -0.10.977 | -0.90.863 | +4.50.386 | -3.10.559 | +4.30.468 | -8.50.096 | +8.60.089 | -4.30.398 |
| Half fence | -2.60.618 | +0.10.977 | 45.6%180 | -0.70.890 | +4.70.386 | -2.90.590 | +4.40.464 | -8.30.114 | +8.80.094 | -4.20.429 |
| Breakable half fence | -1.90.716 | +0.90.863 | +0.70.890 | 46.3%188 | +5.40.313 | -2.20.682 | +5.20.392 | -7.60.144 | +9.50.067 | -3.40.509 |
| Low fence | -7.30.174 | -4.50.386 | -4.70.386 | -5.40.313 | 40.9%159 | -7.60.171 | -0.20.969 | -13.00.017 | +4.10.443 | -8.80.103 |
| Single wall | +0.30.953 | +3.10.559 | +2.90.590 | +2.20.682 | +7.60.171 | 48.5%163 | +7.30.236 | -5.40.316 | +11.70.030 | -1.20.817 |
| Fence and open | -7.00.244 | -4.30.468 | -4.40.464 | -5.20.392 | +0.20.969 | -7.30.236 | 41.1%107 | -12.80.036 | +4.30.468 | -8.60.158 |
| Open | +5.70.270 | +8.50.096 | +8.30.114 | +7.60.144 | +13.00.017 | +5.40.316 | +12.80.036 | 53.9%180 | +17.10.001 | +4.20.429 |
| Rectangle | -11.40.029 | -8.60.089 | -8.80.094 | -9.50.067 | -4.10.443 | -11.70.030 | -4.30.468 | -17.10.001 | 36.8%174 | -12.90.014 |
| Octagon | +1.60.763 | +4.30.398 | +4.20.429 | +3.40.509 | +8.80.103 | +1.20.817 | +8.60.158 | -4.20.429 | +12.90.014 | 49.7%179 |
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 counted104
Win rate51.9%
Widest swing-18.6 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 |
|---|---|---|---|---|---|
| Single wall | 66.7% | +14.8 | 0.354 | 9 · | |
| Breakable full fence | 64.3% | +12.4 | 0.320 | 14 · | |
| Octagon | 64.3% | +12.4 | 0.320 | 14 · | |
| Full fence | 57.1% | +5.2 | 0.674 | 14 · | |
| Fence and open | 50.0% | -1.9 | 0.937 | 4 · | |
| Open | 50.0% | -1.9 | 0.898 | 10 · | |
| Breakable half fence | 33.3% | -18.6 | 0.348 | 6 · | |
| Half fence | 33.3% | -18.6 | 0.243 | 9 · | |
| Low fence | 33.3% | -18.6 | 0.243 | 9 · | |
| Rectangle | 33.3% | -18.6 | 0.243 | 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 7.20 on 9 df, p 0.616
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 57.1%14 | -7.20.699 | +23.80.265 | +23.80.329 | +23.80.265 | -9.50.648 | +7.10.800 | +7.10.729 | +23.80.265 | -7.20.699 |
| Breakable full fence | +7.20.699 | 64.3%14 | +31.00.147 | +31.00.202 | +31.00.147 | -2.40.907 | +14.30.605 | +14.30.484 | +31.00.147 | +0.01.000 |
| Half fence | -23.80.265 | -31.00.147 | 33.3%9 | +0.01.000 | +0.01.000 | -33.30.157 | -16.70.569 | -16.70.463 | +0.01.000 | -31.00.147 |
| Breakable half fence | -23.80.329 | -31.00.202 | -0.01.000 | 33.3%6 | +0.01.000 | -33.30.205 | -16.70.598 | -16.70.515 | +0.01.000 | -31.00.202 |
| Low fence | -23.80.265 | -31.00.147 | -0.01.000 | -0.01.000 | 33.3%9 | -33.30.157 | -16.70.569 | -16.70.463 | +0.01.000 | -31.00.147 |
| Single wall | +9.50.648 | +2.40.907 | +33.30.157 | +33.30.205 | +33.30.157 | 66.7%9 | +16.70.569 | +16.70.463 | +33.30.157 | +2.40.907 |
| Fence and open | -7.10.800 | -14.30.605 | +16.70.569 | +16.70.598 | +16.70.569 | -16.70.569 | 50.0%4 | +0.01.000 | +16.70.569 | -14.30.605 |
| Open | -7.10.729 | -14.30.484 | +16.70.463 | +16.70.515 | +16.70.463 | -16.70.463 | -0.01.000 | 50.0%10 | +16.70.463 | -14.30.484 |
| Rectangle | -23.80.265 | -31.00.147 | -0.01.000 | -0.01.000 | -0.01.000 | -33.30.157 | -16.70.569 | -16.70.463 | 33.3%9 | -31.00.147 |
| Octagon | +7.20.699 | -0.01.000 | +31.00.147 | +31.00.202 | +31.00.147 | -2.40.907 | +14.30.605 | +14.30.484 | +31.00.147 | 64.3%14 |
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.