Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Aoi vs Lion
Matches counted1,703
Win rate45.8%
Widest swing-12.5 pts
Survive correction1
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 |
|---|---|---|---|---|---|
| Rectangle | 51.3% | +5.5 | 0.107 | 187 | |
| Fence and open | 50.5% | +4.7 | 0.341 | 95 | |
| Octagon | 50.3% | +4.5 | 0.204 | 179 | |
| Open | 48.0% | +2.1 | 0.552 | 171 | |
| Breakable half fence | 46.7% | +0.9 | 0.797 | 195 | |
| Full fence | 45.9% | +0.1 | 0.971 | 172 | |
| Half fence | 43.9% | -1.9 | 0.602 | 173 | |
| Breakable full fence | 43.5% | -2.4 | 0.520 | 168 | |
| Low fence | 42.3% | -3.5 | 0.367 | 149 | |
| Single wall | 33.3% | -12.5 | 0.002 | 138 |
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 14.99 on 9 df, p 0.091
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 45.9%172 | +2.50.646 | +2.00.709 | -0.70.888 | +3.60.512 | +12.60.025 | -4.60.472 | -2.00.707 | -5.40.306 | -4.30.415 |
| Breakable full fence | -2.50.646 | 43.5%168 | -0.50.929 | -3.20.540 | +1.20.834 | +10.10.071 | -7.10.269 | -4.50.406 | -7.90.138 | -6.80.203 |
| Half fence | -2.00.709 | +0.50.929 | 43.9%173 | -2.70.599 | +1.60.766 | +10.60.057 | -6.60.300 | -4.00.454 | -7.40.160 | -6.30.233 |
| Breakable half fence | +0.70.888 | +3.20.540 | +2.70.599 | 46.7%195 | +4.40.418 | +13.30.015 | -3.90.537 | -1.30.806 | -4.70.361 | -3.60.485 |
| Low fence | -3.60.512 | -1.20.834 | -1.60.766 | -4.40.418 | 42.3%149 | +8.90.119 | -8.20.207 | -5.70.309 | -9.10.099 | -8.00.148 |
| Single wall | -12.60.025 | -10.10.071 | -10.60.057 | -13.30.015 | -8.90.119 | 33.3%138 | -17.20.009 | -14.60.009 | -18.00.001 | -16.90.003 |
| Fence and open | +4.60.472 | +7.10.269 | +6.60.300 | +3.90.537 | +8.20.207 | +17.20.009 | 50.5%95 | +2.60.687 | -0.80.898 | +0.20.969 |
| Open | +2.00.707 | +4.50.406 | +4.00.454 | +1.30.806 | +5.70.309 | +14.60.009 | -2.60.687 | 48.0%171 | -3.40.522 | -2.30.663 |
| Rectangle | +5.40.306 | +7.90.138 | +7.40.160 | +4.70.361 | +9.10.099 | +18.00.001 | +0.80.898 | +3.40.522 | 51.3%187 | +1.10.840 |
| Octagon | +4.30.415 | +6.80.203 | +6.30.233 | +3.60.485 | +8.00.148 | +16.90.003 | -0.20.969 | +2.30.663 | -1.10.840 | 50.3%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 counted1,491
Win rate45.9%
Widest swing-13.4 pts
Survive correction1
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 | 54.4% | +8.5 | 0.120 | 79 · | |
| Rectangle | 52.2% | +6.2 | 0.093 | 161 | |
| Octagon | 50.3% | +4.4 | 0.233 | 165 | |
| Open | 49.7% | +3.7 | 0.337 | 149 | |
| Breakable half fence | 47.5% | +1.6 | 0.667 | 162 | |
| Full fence | 46.8% | +0.8 | 0.821 | 156 | |
| Breakable full fence | 42.3% | -3.6 | 0.374 | 137 | |
| Half fence | 41.8% | -4.2 | 0.266 | 158 | |
| Low fence | 40.6% | -5.3 | 0.195 | 133 | |
| Single wall | 32.5% | -13.4 | 0.002 | 123 |
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 19.39 on 9 df, p 0.022
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 46.8%156 | +4.50.444 | +5.00.370 | -0.70.895 | +6.20.290 | +14.30.016 | -7.60.269 | -2.90.616 | -5.40.338 | -3.50.530 |
| Breakable full fence | -4.50.444 | 42.3%137 | +0.60.922 | -5.20.368 | +1.70.772 | +9.80.103 | -12.10.086 | -7.30.214 | -9.80.090 | -8.00.167 |
| Half fence | -5.00.370 | -0.60.922 | 41.8%158 | -5.80.300 | +1.20.840 | +9.20.112 | -12.70.065 | -7.90.165 | -10.40.063 | -8.50.124 |
| Breakable half fence | +0.70.895 | +5.20.368 | +5.80.300 | 47.5%162 | +6.90.233 | +15.00.011 | -6.90.315 | -2.10.707 | -4.60.404 | -2.80.616 |
| Low fence | -6.20.290 | -1.70.772 | -1.20.840 | -6.90.233 | 40.6%133 | +8.10.180 | -13.80.051 | -9.10.127 | -11.60.048 | -9.70.095 |
| Single wall | -14.30.016 | -9.80.103 | -9.20.112 | -15.00.011 | -8.10.180 | 32.5%123 | -21.90.002 | -17.10.004 | -19.6<0.001 | -17.80.003 |
| Fence and open | +7.60.269 | +12.10.086 | +12.70.065 | +6.90.315 | +13.80.051 | +21.90.002 | 54.4%79 | +4.80.493 | +2.30.742 | +4.10.546 |
| Open | +2.90.616 | +7.30.214 | +7.90.165 | +2.10.707 | +9.10.127 | +17.10.004 | -4.80.493 | 49.7%149 | -2.50.659 | -0.60.910 |
| Rectangle | +5.40.338 | +9.80.090 | +10.40.063 | +4.60.404 | +11.60.048 | +19.6<0.001 | -2.30.742 | +2.50.659 | 52.2%161 | +1.90.735 |
| Octagon | +3.50.530 | +8.00.167 | +8.50.124 | +2.80.616 | +9.70.095 | +17.80.003 | -4.10.546 | +0.60.910 | -1.90.735 | 50.3%165 |
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 counted212
Win rate44.8%
Widest swing21.9 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 | 66.7% | +21.9 | 0.077 | 15 · | |
| Low fence | 56.2% | +11.4 | 0.339 | 16 · | |
| Octagon | 50.0% | +5.2 | 0.686 | 14 · | |
| Breakable full fence | 48.4% | +3.6 | 0.665 | 31 · | |
| Rectangle | 46.1% | +1.3 | 0.883 | 26 · | |
| Breakable half fence | 42.4% | -2.4 | 0.764 | 33 · | |
| Single wall | 40.0% | -4.8 | 0.697 | 15 · | |
| Full fence | 37.5% | -7.3 | 0.541 | 16 · | |
| Open | 36.4% | -8.4 | 0.400 | 22 · | |
| Fence and open | 31.2% | -13.6 | 0.257 | 16 · |
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 6.45 on 9 df, p 0.694
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 37.5%16 | -10.90.477 | -29.20.104 | -4.90.742 | -18.80.288 | -2.50.886 | +6.20.710 | +1.10.943 | -8.70.582 | -12.50.491 |
| Breakable full fence | +10.90.477 | 48.4%31 | -18.30.243 | +6.00.632 | -7.90.609 | +8.40.592 | +17.10.260 | +12.00.384 | +2.20.866 | -1.60.920 |
| Half fence | +29.20.104 | +18.30.243 | 66.7%15 | +24.20.119 | +10.40.552 | +26.70.143 | +35.40.049 | +30.30.070 | +20.50.205 | +16.70.362 |
| Breakable half fence | +4.90.742 | -6.00.632 | -24.20.119 | 42.4%33 | -13.80.363 | +2.40.875 | +11.20.452 | +6.10.653 | -3.70.775 | -7.60.633 |
| Low fence | +18.80.288 | +7.90.609 | -10.40.552 | +13.80.363 | 56.2%16 | +16.20.366 | +25.00.154 | +19.90.224 | +10.10.525 | +6.20.732 |
| Single wall | +2.50.886 | -8.40.592 | -26.70.143 | -2.40.875 | -16.20.366 | 40.0%15 | +8.80.611 | +3.60.823 | -6.20.702 | -10.00.588 |
| Fence and open | -6.20.710 | -17.10.260 | -35.40.049 | -11.20.452 | -25.00.154 | -8.80.611 | 31.2%16 | -5.10.743 | -14.90.339 | -18.80.296 |
| Open | -1.10.943 | -12.00.384 | -30.30.070 | -6.10.653 | -19.90.224 | -3.60.823 | +5.10.743 | 36.4%22 | -9.80.493 | -13.60.418 |
| Rectangle | +8.70.582 | -2.20.866 | -20.50.205 | +3.70.775 | -10.10.525 | +6.20.702 | +14.90.339 | +9.80.493 | 46.1%26 | -3.90.816 |
| Octagon | +12.50.491 | +1.60.920 | -16.70.362 | +7.60.633 | -6.20.732 | +10.00.588 | +18.80.296 | +13.60.418 | +3.90.816 | 50.0%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.