Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Aoi vs Shun
Matches counted1,650
Win rate49.0%
Widest swing-10.4 pts
Survive correction2
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 |
|---|---|---|---|---|---|
| Full fence | 58.1% | +9.1 | 0.010 | 179 | |
| Breakable full fence | 53.4% | +4.4 | 0.214 | 178 | |
| Half fence | 53.2% | +4.3 | 0.240 | 169 | |
| Open | 51.7% | +2.7 | 0.488 | 149 | |
| Rectangle | 50.3% | +1.4 | 0.724 | 153 | |
| Fence and open | 48.6% | -0.4 | 0.946 | 70 · | |
| Breakable half fence | 47.3% | -1.7 | 0.631 | 186 | |
| Low fence | 45.9% | -3.1 | 0.417 | 159 | |
| Single wall | 43.0% | -5.9 | 0.108 | 165 | |
| Octagon | 38.6% | -10.4 | 0.007 | 153 |
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 18.87 on 9 df, p 0.026
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 58.1%179 | +4.70.368 | +4.80.363 | +10.80.039 | +12.20.025 | +15.10.005 | +9.50.174 | +6.40.244 | +7.80.156 | +19.5<0.001 |
| Breakable full fence | -4.70.368 | 53.4%178 | +0.10.983 | +6.10.248 | +7.50.172 | +10.30.056 | +4.80.496 | +1.70.760 | +3.00.581 | +14.80.007 |
| Half fence | -4.80.363 | -0.10.983 | 53.2%169 | +5.90.263 | +7.30.184 | +10.20.062 | +4.70.510 | +1.60.779 | +2.90.600 | +14.70.008 |
| Breakable half fence | -10.80.039 | -6.10.248 | -5.90.263 | 47.3%186 | +1.40.795 | +4.30.421 | -1.30.857 | -4.40.427 | -3.00.580 | +8.80.106 |
| Low fence | -12.20.025 | -7.50.172 | -7.30.184 | -1.40.795 | 45.9%159 | +2.90.602 | -2.70.710 | -5.80.312 | -4.40.435 | +7.30.189 |
| Single wall | -15.10.005 | -10.30.056 | -10.20.062 | -4.30.421 | -2.90.602 | 43.0%165 | -5.50.435 | -8.70.125 | -7.30.192 | +4.50.418 |
| Fence and open | -9.50.174 | -4.80.496 | -4.70.510 | +1.30.857 | +2.70.710 | +5.50.435 | 48.6%70 | -3.10.668 | -1.80.808 | +10.00.159 |
| Open | -6.40.244 | -1.70.760 | -1.60.779 | +4.40.427 | +5.80.312 | +8.70.125 | +3.10.668 | 51.7%149 | +1.40.814 | +13.10.022 |
| Rectangle | -7.80.156 | -3.00.581 | -2.90.600 | +3.00.580 | +4.40.435 | +7.30.192 | +1.80.808 | -1.40.814 | 50.3%153 | +11.80.038 |
| Octagon | -19.5<0.001 | -14.80.007 | -14.70.008 | -8.80.106 | -7.30.189 | -4.50.418 | -10.00.159 | -13.10.022 | -11.80.038 | 38.6%153 |
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 counted1,415
Win rate49.0%
Widest swing-9.6 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 |
|---|---|---|---|---|---|
| Full fence | 58.3% | +9.3 | 0.012 | 163 | |
| Breakable full fence | 52.6% | +3.6 | 0.340 | 152 | |
| Half fence | 51.5% | +2.5 | 0.540 | 134 | |
| Rectangle | 51.5% | +2.5 | 0.540 | 134 | |
| Fence and open | 50.0% | +1.0 | 0.869 | 62 · | |
| Open | 49.6% | +0.6 | 0.890 | 119 | |
| Breakable half fence | 47.1% | -1.9 | 0.616 | 153 | |
| Low fence | 46.9% | -2.1 | 0.592 | 143 | |
| Single wall | 43.9% | -5.1 | 0.206 | 139 | |
| Octagon | 39.4% | -9.6 | 0.021 | 132 |
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 13.93 on 9 df, p 0.125
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 58.3%163 | +5.70.313 | +6.80.242 | +11.20.046 | +11.40.046 | +14.40.013 | +8.30.263 | +8.70.147 | +6.80.242 | +18.90.001 |
| Breakable full fence | -5.70.313 | 52.6%152 | +1.10.847 | +5.60.330 | +5.80.321 | +8.80.136 | +2.60.727 | +3.00.618 | +1.10.847 | +13.20.026 |
| Half fence | -6.80.242 | -1.10.847 | 51.5%134 | +4.40.454 | +4.60.440 | +7.60.208 | +1.50.846 | +1.90.761 | +0.01.000 | +12.10.048 |
| Breakable half fence | -11.20.046 | -5.60.330 | -4.40.454 | 47.1%153 | +0.20.972 | +3.20.587 | -2.90.696 | -2.50.680 | -4.40.454 | +7.70.193 |
| Low fence | -11.40.046 | -5.80.321 | -4.60.440 | -0.20.972 | 46.9%143 | +3.00.617 | -3.10.679 | -2.70.660 | -4.60.440 | +7.50.212 |
| Single wall | -14.40.013 | -8.80.136 | -7.60.208 | -3.20.587 | -3.00.617 | 43.9%139 | -6.10.422 | -5.70.361 | -7.60.208 | +4.50.454 |
| Fence and open | -8.30.263 | -2.60.727 | -1.50.846 | +2.90.696 | +3.10.679 | +6.10.422 | 50.0%62 | +0.40.957 | -1.50.846 | +10.60.164 |
| Open | -8.70.147 | -3.00.618 | -1.90.761 | +2.50.680 | +2.70.660 | +5.70.361 | -0.40.957 | 49.6%119 | -1.90.761 | +10.20.105 |
| Rectangle | -6.80.242 | -1.10.847 | -0.01.000 | +4.40.454 | +4.60.440 | +7.60.208 | +1.50.846 | +1.90.761 | 51.5%134 | +12.10.048 |
| Octagon | -18.90.001 | -13.20.026 | -12.10.048 | -7.70.193 | -7.50.212 | -4.50.454 | -10.60.164 | -10.20.105 | -12.10.048 | 39.4%132 |
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 counted235
Win rate48.9%
Widest swing-15.6 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 |
|---|---|---|---|---|---|
| Half fence | 60.0% | +11.1 | 0.156 | 35 · | |
| Open | 60.0% | +11.1 | 0.194 | 30 · | |
| Breakable full fence | 57.7% | +8.8 | 0.344 | 26 · | |
| Full fence | 56.2% | +7.3 | 0.544 | 16 · | |
| Breakable half fence | 48.5% | -0.5 | 0.955 | 33 · | |
| Rectangle | 42.1% | -6.8 | 0.534 | 19 · | |
| Single wall | 38.5% | -10.5 | 0.257 | 26 · | |
| Fence and open | 37.5% | -11.4 | 0.510 | 8 · | |
| Low fence | 37.5% | -11.4 | 0.343 | 16 · | |
| Octagon | 33.3% | -15.6 | 0.134 | 21 · |
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 9.12 on 9 df, p 0.426
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 56.2%16 | -1.40.927 | -3.80.801 | +7.80.610 | +18.80.288 | +17.80.261 | +18.80.386 | -3.80.806 | +14.10.404 | +22.90.163 |
| Breakable full fence | +1.40.927 | 57.7%26 | -2.30.856 | +9.20.482 | +20.20.204 | +19.20.165 | +20.20.317 | -2.30.861 | +15.60.302 | +24.40.096 |
| Half fence | +3.80.801 | +2.30.856 | 60.0%35 | +11.50.341 | +22.50.135 | +21.50.096 | +22.50.248 | +0.01.000 | +17.90.208 | +26.70.053 |
| Breakable half fence | -7.80.610 | -9.20.482 | -11.50.341 | 48.5%33 | +11.00.468 | +10.00.441 | +11.00.576 | -11.50.360 | +6.40.657 | +15.20.272 |
| Low fence | -18.80.288 | -20.20.204 | -22.50.135 | -11.00.468 | 37.5%16 | -1.00.950 | +0.01.000 | -22.50.146 | -4.60.782 | +4.20.793 |
| Single wall | -17.80.261 | -19.20.165 | -21.50.096 | -10.00.441 | +1.00.950 | 38.5%26 | +1.00.961 | -21.50.108 | -3.60.805 | +5.10.716 |
| Fence and open | -18.80.386 | -20.20.317 | -22.50.248 | -11.00.576 | -0.01.000 | -1.00.961 | 37.5%8 | -22.50.255 | -4.60.824 | +4.20.833 |
| Open | +3.80.806 | +2.30.861 | -0.01.000 | +11.50.360 | +22.50.146 | +21.50.108 | +22.50.255 | 60.0%30 | +17.90.221 | +26.70.061 |
| Rectangle | -14.10.404 | -15.60.302 | -17.90.208 | -6.40.657 | +4.60.782 | +3.60.805 | +4.60.824 | -17.90.221 | 42.1%19 | +8.80.567 |
| Octagon | -22.90.163 | -24.40.096 | -26.70.053 | -15.20.272 | -4.20.793 | -5.10.716 | -4.20.833 | -26.70.061 | -8.80.567 | 33.3%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.