Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Jean vs Taka
Matches counted644
Win rate53.4%
Widest swing17.7 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Jean's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Octagon | 71.1% | +17.7 | 0.014 | 45 · | |
| Low fence | 60.0% | +6.6 | 0.306 | 55 · | |
| Single wall | 58.2% | +4.8 | 0.459 | 55 · | |
| Half fence | 54.9% | +1.5 | 0.786 | 71 · | |
| Open | 54.4% | +1.0 | 0.862 | 68 · | |
| Full fence | 51.9% | -1.6 | 0.810 | 54 · | |
| Breakable half fence | 51.4% | -2.1 | 0.705 | 74 · | |
| Fence and open | 48.4% | -5.0 | 0.565 | 31 · | |
| Rectangle | 47.4% | -6.0 | 0.259 | 78 · | |
| Breakable full fence | 44.2% | -9.2 | 0.065 | 86 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Jean's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 11.77 on 9 df, p 0.227
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 51.9%54 | +7.70.376 | -3.10.733 | +0.50.955 | -8.20.392 | -6.30.507 | +3.50.758 | -2.60.778 | +4.40.618 | -19.30.051 |
| Breakable full fence | -7.70.376 | 44.2%86 | -10.70.180 | -7.20.366 | -15.80.067 | -14.00.105 | -4.20.687 | -10.20.207 | -3.20.677 | -26.90.003 |
| Half fence | +3.10.733 | +10.70.180 | 54.9%71 | +3.60.666 | -5.10.568 | -3.20.715 | +6.50.543 | +0.50.951 | +7.50.361 | -16.20.081 |
| Breakable half fence | -0.50.955 | +7.20.366 | -3.60.666 | 51.4%74 | -8.70.329 | -6.80.441 | +3.00.782 | -3.10.715 | +3.90.629 | -19.80.034 |
| Low fence | +8.20.392 | +15.80.067 | +5.10.568 | +8.70.329 | 60.0%55 | +1.80.846 | +11.60.298 | +5.60.534 | +12.60.153 | -11.10.246 |
| Single wall | +6.30.507 | +14.00.105 | +3.20.715 | +6.80.441 | -1.80.846 | 58.2%55 | +9.80.381 | +3.80.675 | +10.70.222 | -12.90.180 |
| Fence and open | -3.50.758 | +4.20.687 | -6.50.543 | -3.00.782 | -11.60.298 | -9.80.381 | 48.4%31 | -6.00.578 | +0.90.929 | -22.70.045 |
| Open | +2.60.778 | +10.20.207 | -0.50.951 | +3.10.715 | -5.60.534 | -3.80.675 | +6.00.578 | 54.4%68 | +7.00.400 | -16.70.075 |
| Rectangle | -4.40.618 | +3.20.677 | -7.50.361 | -3.90.629 | -12.60.153 | -10.70.222 | -0.90.929 | -7.00.400 | 47.4%78 | -23.70.011 |
| Octagon | +19.30.051 | +26.90.003 | +16.20.081 | +19.80.034 | +11.10.246 | +12.90.180 | +22.70.045 | +16.70.075 | +23.70.011 | 71.1%45 |
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 counted544
Win rate51.5%
Widest swing19.3 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Jean's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Octagon | 70.7% | +19.3 | 0.010 | 41 · | |
| Low fence | 59.0% | +7.5 | 0.330 | 39 · | |
| Half fence | 56.5% | +5.0 | 0.404 | 62 · | |
| Single wall | 56.2% | +4.8 | 0.488 | 48 · | |
| Full fence | 50.0% | -1.5 | 0.831 | 48 · | |
| Fence and open | 48.4% | -3.1 | 0.724 | 31 · | |
| Open | 48.3% | -3.1 | 0.606 | 60 · | |
| Rectangle | 45.6% | -5.9 | 0.299 | 68 · | |
| Breakable full fence | 44.3% | -7.2 | 0.232 | 61 · | |
| Breakable half fence | 43.5% | -7.9 | 0.185 | 62 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Jean's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 12.18 on 9 df, p 0.203
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 50.0%48 | +5.70.551 | -6.50.501 | +6.50.501 | -9.00.404 | -6.20.539 | +1.60.889 | +1.70.863 | +4.40.639 | -20.70.047 |
| Breakable full fence | -5.70.551 | 44.3%61 | -12.20.176 | +0.70.936 | -14.70.151 | -12.00.214 | -4.10.707 | -4.10.653 | -1.30.880 | -26.50.008 |
| Half fence | +6.50.501 | +12.20.176 | 56.5%62 | +12.90.151 | -2.50.803 | +0.20.983 | +8.10.462 | +8.10.369 | +10.90.216 | -14.30.144 |
| Breakable half fence | -6.50.501 | -0.70.936 | -12.90.151 | 43.5%62 | -15.40.131 | -12.70.186 | -4.80.658 | -4.80.596 | -2.00.815 | -27.20.007 |
| Low fence | +9.00.404 | +14.70.151 | +2.50.803 | +15.40.131 | 59.0%39 | +2.70.798 | +10.60.377 | +10.60.300 | +13.40.183 | -11.80.270 |
| Single wall | +6.20.539 | +12.00.214 | -0.20.983 | +12.70.186 | -2.70.798 | 56.2%48 | +7.90.494 | +7.90.413 | +10.70.258 | -14.50.159 |
| Fence and open | -1.60.889 | +4.10.707 | -8.10.462 | +4.80.658 | -10.60.377 | -7.90.494 | 48.4%31 | +0.10.996 | +2.80.796 | -22.30.054 |
| Open | -1.70.863 | +4.10.653 | -8.10.369 | +4.80.596 | -10.60.300 | -7.90.413 | -0.10.996 | 48.3%60 | +2.70.756 | -22.40.025 |
| Rectangle | -4.40.639 | +1.30.880 | -10.90.216 | +2.00.815 | -13.40.183 | -10.70.258 | -2.80.796 | -2.70.756 | 45.6%68 | -25.10.011 |
| Octagon | +20.70.047 | +26.50.008 | +14.30.144 | +27.20.007 | +11.80.270 | +14.50.159 | +22.30.054 | +22.40.025 | +25.10.011 | 70.7%41 |
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 counted100
Win rate64.0%
Widest swing36.0 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Jean's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Open | 100.0% | +36.0 | 0.027 | 8 · | |
| Breakable half fence | 91.7% | +27.7 | 0.033 | 12 · | |
| Octagon | 75.0% | +11.0 | 0.640 | 4 · | |
| Single wall | 71.4% | +7.4 | 0.671 | 7 · | |
| Full fence | 66.7% | +2.7 | 0.888 | 6 · | |
| Low fence | 62.5% | -1.5 | 0.892 | 16 · | |
| Rectangle | 60.0% | -4.0 | 0.781 | 10 · | |
| Half fence | 44.4% | -19.6 | 0.200 | 9 · | |
| Breakable full fence | 44.0% | -20.0 | 0.016 | 25 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Jean's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 14.79 on 8 df, p 0.063
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|
| Full fence | 66.7%6 | +22.70.318 | +22.20.398 | -25.00.180 | +4.20.856 | -4.80.853 | -33.30.078 | +6.70.790 | -8.30.778 |
| Breakable full fence | -22.70.318 | 44.0%25 | -0.40.982 | -47.70.006 | -18.50.248 | -27.40.200 | -56.00.005 | -16.00.392 | -31.00.249 |
| Half fence | -22.20.398 | +0.40.982 | 44.4%9 | -47.20.018 | -18.10.383 | -27.00.280 | -55.60.012 | -15.60.498 | -30.60.308 |
| Breakable half fence | +25.00.180 | +47.70.006 | +47.20.018 | 91.7%12 | +29.20.078 | +20.20.243 | -8.30.402 | +31.70.078 | +16.70.383 |
| Low fence | -4.20.856 | +18.50.248 | +18.10.383 | -29.20.078 | 62.5%16 | -8.90.679 | -37.50.046 | +2.50.899 | -12.50.639 |
| Single wall | +4.80.853 | +27.40.200 | +27.00.280 | -20.20.243 | +8.90.679 | 71.4%7 | -28.60.104 | +11.40.627 | -3.60.898 |
| Open | +33.30.078 | +56.00.005 | +55.60.012 | +8.30.402 | +37.50.046 | +28.60.104 | 100.0%8 | +40.00.043 | +25.00.140 |
| Rectangle | -6.70.790 | +16.00.392 | +15.60.498 | -31.70.078 | -2.50.899 | -11.40.627 | -40.00.043 | 60.0%10 | -15.00.597 |
| Octagon | +8.30.778 | +31.00.249 | +30.60.308 | -16.70.383 | +12.50.639 | +3.60.898 | -25.00.140 | +15.00.597 | 75.0%4 |
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.