Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Jean vs Sarah
Matches counted2,094
Win rate47.4%
Widest swing-6.2 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 |
|---|---|---|---|---|---|
| Breakable full fence | 51.7% | +4.3 | 0.195 | 207 | |
| Rectangle | 50.7% | +3.3 | 0.305 | 221 | |
| Single wall | 49.3% | +1.8 | 0.581 | 203 | |
| Low fence | 48.4% | +0.9 | 0.750 | 246 | |
| Octagon | 48.2% | +0.8 | 0.792 | 228 | |
| Open | 47.5% | +0.0 | 0.993 | 196 | |
| Half fence | 45.0% | -2.4 | 0.471 | 200 | |
| Breakable half fence | 44.1% | -3.3 | 0.301 | 222 | |
| Full fence | 43.8% | -3.6 | 0.314 | 178 | |
| Fence and open | 41.2% | -6.2 | 0.212 | 97 |
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 6.72 on 9 df, p 0.666
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 43.8%178 | -7.90.123 | -1.20.818 | -0.30.948 | -4.50.353 | -5.40.288 | +2.60.679 | -3.60.482 | -6.90.173 | -4.40.375 |
| Breakable full fence | +7.90.123 | 51.7%207 | +6.70.177 | +7.50.118 | +3.30.482 | +2.40.623 | +10.40.089 | +4.20.395 | +1.00.834 | +3.40.473 |
| Half fence | +1.20.818 | -6.70.177 | 45.0%200 | +0.90.860 | -3.40.478 | -4.30.392 | +3.80.540 | -2.50.625 | -5.70.244 | -3.20.502 |
| Breakable half fence | +0.30.948 | -7.50.118 | -0.90.860 | 44.1%222 | -4.20.360 | -5.10.291 | +2.90.630 | -3.30.498 | -6.50.168 | -4.10.383 |
| Low fence | +4.50.353 | -3.30.482 | +3.40.478 | +4.20.360 | 48.4%246 | -0.90.852 | +7.10.233 | +0.90.847 | -2.30.619 | +0.10.978 |
| Single wall | +5.40.288 | -2.40.623 | +4.30.392 | +5.10.291 | +0.90.852 | 49.3%203 | +8.00.193 | +1.80.717 | -1.40.771 | +1.00.833 |
| Fence and open | -2.60.679 | -10.40.089 | -3.80.540 | -2.90.630 | -7.10.233 | -8.00.193 | 41.2%97 | -6.20.315 | -9.40.121 | -7.00.246 |
| Open | +3.60.482 | -4.20.395 | +2.50.625 | +3.30.498 | -0.90.847 | -1.80.717 | +6.20.315 | 47.5%196 | -3.20.510 | -0.80.870 |
| Rectangle | +6.90.173 | -1.00.834 | +5.70.244 | +6.50.168 | +2.30.619 | +1.40.771 | +9.40.121 | +3.20.510 | 50.7%221 | +2.40.606 |
| Octagon | +4.40.375 | -3.40.473 | +3.20.502 | +4.10.383 | -0.10.978 | -1.00.833 | +7.00.246 | +0.80.870 | -2.40.606 | 48.2%228 |
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 counted2,023
Win rate47.4%
Widest swing-5.7 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 |
|---|---|---|---|---|---|
| Breakable full fence | 51.5% | +4.2 | 0.218 | 196 | |
| Rectangle | 51.4% | +4.0 | 0.210 | 214 | |
| Single wall | 48.5% | +1.1 | 0.738 | 198 | |
| Octagon | 48.4% | +1.0 | 0.752 | 215 | |
| Low fence | 48.2% | +0.8 | 0.787 | 245 | |
| Open | 47.4% | +0.0 | 0.997 | 190 | |
| Breakable half fence | 44.1% | -3.3 | 0.313 | 211 | |
| Half fence | 44.0% | -3.3 | 0.332 | 193 | |
| Full fence | 43.8% | -3.6 | 0.316 | 176 | |
| Fence and open | 41.7% | -5.7 | 0.253 | 96 |
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 6.95 on 9 df, p 0.642
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 43.8%176 | -7.80.134 | -0.30.955 | -0.30.949 | -4.40.370 | -4.70.359 | +2.10.740 | -3.60.487 | -7.70.132 | -4.60.362 |
| Breakable full fence | +7.80.134 | 51.5%196 | +7.50.139 | +7.50.132 | +3.40.482 | +3.00.545 | +9.90.113 | +4.20.414 | +0.10.979 | +3.20.522 |
| Half fence | +0.30.955 | -7.50.139 | 44.0%193 | -0.00.994 | -4.10.390 | -4.40.378 | +2.40.701 | -3.30.513 | -7.40.138 | -4.30.381 |
| Breakable half fence | +0.30.949 | -7.50.132 | +0.00.994 | 44.1%211 | -4.10.383 | -4.40.371 | +2.40.693 | -3.30.509 | -7.30.131 | -4.30.374 |
| Low fence | +4.40.370 | -3.40.482 | +4.10.390 | +4.10.383 | 48.2%245 | -0.30.946 | +6.50.279 | +0.80.869 | -3.20.489 | -0.20.964 |
| Single wall | +4.70.359 | -3.00.545 | +4.40.378 | +4.40.371 | +0.30.946 | 48.5%198 | +6.80.272 | +1.10.826 | -2.90.554 | +0.10.982 |
| Fence and open | -2.10.740 | -9.90.113 | -2.40.701 | -2.40.693 | -6.50.279 | -6.80.272 | 41.7%96 | -5.70.360 | -9.70.113 | -6.70.273 |
| Open | +3.60.487 | -4.20.414 | +3.30.513 | +3.30.509 | -0.80.869 | -1.10.826 | +5.70.360 | 47.4%190 | -4.00.418 | -1.00.840 |
| Rectangle | +7.70.132 | -0.10.979 | +7.40.138 | +7.30.131 | +3.20.489 | +2.90.554 | +9.70.113 | +4.00.418 | 51.4%214 | +3.00.530 |
| Octagon | +4.60.362 | -3.20.522 | +4.30.381 | +4.30.374 | +0.20.964 | -0.10.982 | +6.70.273 | +1.00.840 | -3.00.530 | 48.4%215 |
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 counted71
Win rate49.3%
Widest swing50.7 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 |
|---|---|---|---|---|---|
| Low fence | 100.0% | +50.7 | 0.307 | 1 · | |
| Single wall | 80.0% | +30.7 | 0.154 | 5 · | |
| Half fence | 71.4% | +22.1 | 0.217 | 7 · | |
| Breakable full fence | 54.5% | +5.2 | 0.705 | 11 · | |
| Full fence | 50.0% | +0.7 | 0.984 | 2 · | |
| Open | 50.0% | +0.7 | 0.971 | 6 · | |
| Octagon | 46.1% | -3.1 | 0.802 | 13 · | |
| Breakable half fence | 45.5% | -3.9 | 0.782 | 11 · | |
| Rectangle | 28.6% | -20.7 | 0.248 | 7 · | |
| Fence and open | 0.0% | -49.3 | 0.321 | 1 · |
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 6.57 on 9 df, p 0.681
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 50.0%2 | -4.50.906 | -21.40.571 | +4.50.906 | -50.00.386 | -30.00.427 | +50.00.386 | +0.01.000 | +21.40.571 | +3.90.919 |
| Breakable full fence | +4.50.906 | 54.5%11 | -16.90.474 | +9.10.670 | -45.50.377 | -25.40.330 | +54.50.296 | +4.50.858 | +26.00.280 | +8.40.682 |
| Half fence | +21.40.571 | +16.90.474 | 71.4%7 | +26.00.280 | -28.60.537 | -8.60.735 | +71.40.168 | +21.40.429 | +42.90.109 | +25.30.279 |
| Breakable half fence | -4.50.906 | -9.10.670 | -26.00.280 | 45.5%11 | -54.50.296 | -34.50.197 | +45.50.377 | -4.50.858 | +16.90.474 | -0.70.973 |
| Low fence | +50.00.386 | +45.50.377 | +28.60.537 | +54.50.296 | 100.0%1 | +20.00.624 | +100.00.157 | +50.00.350 | +71.40.168 | +53.90.299 |
| Single wall | +30.00.427 | +25.40.330 | +8.60.735 | +34.50.197 | -20.00.624 | 80.0%5 | +80.00.121 | +30.00.303 | +51.40.079 | +33.90.196 |
| Fence and open | -50.00.386 | -54.50.296 | -71.40.168 | -45.50.377 | -100.00.157 | -80.00.121 | 0.0%1 | -50.00.350 | -28.60.537 | -46.10.369 |
| Open | -0.01.000 | -4.50.858 | -21.40.429 | +4.50.858 | -50.00.350 | -30.00.303 | +50.00.350 | 50.0%6 | +21.40.429 | +3.90.876 |
| Rectangle | -21.40.571 | -26.00.280 | -42.90.109 | -16.90.474 | -71.40.168 | -51.40.079 | +28.60.537 | -21.40.429 | 28.6%7 | -17.60.444 |
| Octagon | -3.90.919 | -8.40.682 | -25.30.279 | +0.70.973 | -53.90.299 | -33.90.196 | +46.10.369 | -3.90.876 | +17.60.444 | 46.1%13 |
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.