Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Aoi vs Lau
Matches counted2,099
Win rate48.0%
Widest swing-13.2 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 |
|---|---|---|---|---|---|
| Breakable half fence | 54.9% | +6.9 | 0.044 | 193 | |
| Low fence | 52.5% | +4.5 | 0.160 | 217 | |
| Octagon | 51.5% | +3.5 | 0.302 | 196 | |
| Open | 51.5% | +3.5 | 0.260 | 233 | |
| Single wall | 49.5% | +1.5 | 0.660 | 200 | |
| Rectangle | 47.2% | -0.8 | 0.798 | 214 | |
| Full fence | 45.9% | -2.1 | 0.491 | 231 | |
| Half fence | 45.5% | -2.5 | 0.439 | 211 | |
| Fence and open | 41.2% | -6.8 | 0.171 | 97 | |
| Breakable full fence | 34.8% | -13.2 | <0.001 | 204 |
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 24.78 on 9 df, p 0.003
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 45.9%231 | +11.10.019 | +0.40.935 | -9.00.064 | -6.60.160 | -3.60.454 | +4.70.439 | -5.60.226 | -1.30.782 | -5.60.245 |
| Breakable full fence | -11.10.019 | 34.8%204 | -10.70.026 | -20.1<0.001 | -17.7<0.001 | -14.70.003 | -6.40.280 | -16.7<0.001 | -12.40.010 | -16.7<0.001 |
| Half fence | -0.40.935 | +10.70.026 | 45.5%211 | -9.40.058 | -7.00.145 | -4.00.417 | +4.30.484 | -6.00.206 | -1.70.726 | -6.00.224 |
| Breakable half fence | +9.00.064 | +20.1<0.001 | +9.40.058 | 54.9%193 | +2.40.628 | +5.40.282 | +13.70.028 | +3.40.481 | +7.70.120 | +3.40.503 |
| Low fence | +6.60.160 | +17.7<0.001 | +7.00.145 | -2.40.628 | 52.5%217 | +3.00.536 | +11.30.064 | +1.00.827 | +5.30.268 | +1.00.838 |
| Single wall | +3.60.454 | +14.70.003 | +4.00.417 | -5.40.282 | -3.00.536 | 49.5%200 | +8.30.181 | -2.00.678 | +2.30.639 | -2.00.686 |
| Fence and open | -4.70.439 | +6.40.280 | -4.30.484 | -13.70.028 | -11.30.064 | -8.30.181 | 41.2%97 | -10.30.089 | -6.00.328 | -10.30.097 |
| Open | +5.60.226 | +16.7<0.001 | +6.00.206 | -3.40.481 | -1.00.827 | +2.00.678 | +10.30.089 | 51.5%233 | +4.30.363 | -0.00.995 |
| Rectangle | +1.30.782 | +12.40.010 | +1.70.726 | -7.70.120 | -5.30.268 | -2.30.639 | +6.00.328 | -4.30.363 | 47.2%214 | -4.30.381 |
| Octagon | +5.60.245 | +16.7<0.001 | +6.00.224 | -3.40.503 | -1.00.838 | +2.00.686 | +10.30.097 | +0.00.995 | +4.30.381 | 51.5%196 |
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 counted1,682
Win rate49.8%
Widest swing-15.0 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 |
|---|---|---|---|---|---|
| Breakable half fence | 57.8% | +8.0 | 0.042 | 147 | |
| Low fence | 56.1% | +6.2 | 0.083 | 173 | |
| Octagon | 52.4% | +2.6 | 0.484 | 168 | |
| Open | 52.2% | +2.4 | 0.494 | 178 | |
| Single wall | 52.2% | +2.4 | 0.528 | 159 | |
| Full fence | 49.0% | -0.8 | 0.801 | 194 | |
| Rectangle | 48.5% | -1.3 | 0.718 | 165 | |
| Fence and open | 46.2% | -3.6 | 0.513 | 80 | |
| Half fence | 45.9% | -3.9 | 0.281 | 172 | |
| Breakable full fence | 34.8% | -15.0 | <0.001 | 161 |
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 23.86 on 9 df, p 0.005
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 49.0%194 | +14.20.007 | +3.00.561 | -8.80.105 | -7.10.174 | -3.20.546 | +2.70.682 | -3.30.528 | +0.50.927 | -3.40.517 |
| Breakable full fence | -14.20.007 | 34.8%161 | -11.20.038 | -23.0<0.001 | -21.3<0.001 | -17.40.002 | -11.50.085 | -17.50.001 | -13.70.012 | -17.60.001 |
| Half fence | -3.00.561 | +11.20.038 | 45.9%172 | -11.90.034 | -10.10.060 | -6.30.254 | -0.30.962 | -6.30.237 | -2.50.639 | -6.50.234 |
| Breakable half fence | +8.80.105 | +23.0<0.001 | +11.90.034 | 57.8%147 | +1.80.752 | +5.60.323 | +11.60.095 | +5.60.315 | +9.30.099 | +5.40.333 |
| Low fence | +7.10.174 | +21.3<0.001 | +10.10.060 | -1.80.752 | 56.1%173 | +3.90.480 | +9.80.146 | +3.80.472 | +7.60.163 | +3.70.494 |
| Single wall | +3.20.546 | +17.40.002 | +6.30.254 | -5.60.323 | -3.90.480 | 52.2%159 | +6.00.385 | -0.10.993 | +3.70.504 | -0.20.974 |
| Fence and open | -2.70.682 | +11.50.085 | +0.30.962 | -11.60.095 | -9.80.146 | -6.00.385 | 46.2%80 | -6.00.373 | -2.20.743 | -6.10.367 |
| Open | +3.30.528 | +17.50.001 | +6.30.237 | -5.60.315 | -3.80.472 | +0.10.993 | +6.00.373 | 52.2%178 | +3.80.486 | -0.10.980 |
| Rectangle | -0.50.927 | +13.70.012 | +2.50.639 | -9.30.099 | -7.60.163 | -3.70.504 | +2.20.743 | -3.80.486 | 48.5%165 | -3.90.477 |
| Octagon | +3.40.517 | +17.60.001 | +6.50.234 | -5.40.333 | -3.70.494 | +0.20.974 | +6.10.367 | +0.10.980 | +3.90.477 | 52.4%168 |
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 counted417
Win rate40.8%
Widest swing-23.1 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 | 49.1% | +8.3 | 0.178 | 55 · | |
| Octagon | 46.4% | +5.7 | 0.528 | 28 · | |
| Breakable half fence | 45.6% | +4.9 | 0.475 | 46 · | |
| Half fence | 43.6% | +2.8 | 0.706 | 39 · | |
| Rectangle | 42.9% | +2.1 | 0.751 | 49 · | |
| Single wall | 39.0% | -1.8 | 0.811 | 41 · | |
| Low fence | 38.6% | -2.1 | 0.761 | 44 · | |
| Breakable full fence | 34.9% | -5.9 | 0.407 | 43 · | |
| Full fence | 29.7% | -11.0 | 0.152 | 37 · | |
| Fence and open | 17.6% | -23.1 | 0.048 | 17 · |
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 9.00 on 9 df, p 0.437
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 29.7%37 | -5.20.624 | -13.90.211 | -15.90.139 | -8.90.401 | -9.30.389 | +12.10.347 | -19.40.064 | -13.10.212 | -16.70.167 |
| Breakable full fence | +5.20.624 | 34.9%43 | -8.70.420 | -10.80.301 | -3.80.717 | -4.10.694 | +17.20.189 | -14.20.158 | -8.00.434 | -11.60.331 |
| Half fence | +13.90.211 | +8.70.420 | 43.6%39 | -2.10.849 | +5.00.647 | +4.60.678 | +25.90.062 | -5.50.598 | +0.70.945 | -2.80.818 |
| Breakable half fence | +15.90.139 | +10.80.301 | +2.10.849 | 45.6%46 | +7.00.501 | +6.60.533 | +28.00.042 | -3.40.730 | +2.80.784 | -0.80.948 |
| Low fence | +8.90.401 | +3.80.717 | -5.00.647 | -7.00.501 | 38.6%44 | -0.40.971 | +21.00.117 | -10.40.298 | -4.20.679 | -7.80.513 |
| Single wall | +9.30.389 | +4.10.694 | -4.60.678 | -6.60.533 | +0.40.971 | 39.0%41 | +21.40.114 | -10.10.327 | -3.80.713 | -7.40.541 |
| Fence and open | -12.10.347 | -17.20.189 | -25.90.062 | -28.00.042 | -21.00.117 | -21.40.114 | 17.6%17 | -31.40.022 | -25.20.063 | -28.80.051 |
| Open | +19.40.064 | +14.20.158 | +5.50.598 | +3.40.730 | +10.40.298 | +10.10.327 | +31.40.022 | 49.1%55 | +6.20.524 | +2.70.818 |
| Rectangle | +13.10.212 | +8.00.434 | -0.70.945 | -2.80.784 | +4.20.679 | +3.80.713 | +25.20.063 | -6.20.524 | 42.9%49 | -3.60.761 |
| Octagon | +16.70.167 | +11.60.331 | +2.80.818 | +0.80.948 | +7.80.513 | +7.40.541 | +28.80.051 | -2.70.818 | +3.60.761 | 46.4%28 |
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.