| Kumiko vs Kazuya | 57–37 | 60.64% |
| Kumiko vs Dragunov | 59–33 | 64.13% |
| Kumiko vs Jin | 51–32 | 61.45% |
| Kumiko vs Bryan | 46–35 | 56.79% |
| Kumiko vs Reina | 42–38 | 52.50% |
| Kumiko vs King | 39–28 | 58.21% |
| Kumiko vs Yoshimitsu | 38–28 | 57.58% |
| Kumiko vs Steve | 50–16 | 75.76% |
| Kumiko vs Hwoarang | 42–23 | 64.62% |
| Kumiko vs Victor | 28–28 | 50.00% |
| Kumiko vs Heihachi | 28–22 | 56.00% |
| Kumiko vs Law | 29–17 | 63.04% |
| Kumiko vs Paul | 22–22 | 50.00% |
| Kumiko vs Asuka | 23–17 | 57.50% |
| Kumiko vs Jun | 22–14 | 61.11% |
| Kumiko vs Devil Jin | 24–10 | 70.59% |
| Kumiko vs Lili | 18–16 | 52.94% |
| Kumiko vs Lars | 18–15 | 54.55% |
| Kumiko vs Lee | 13–19 | 40.62% |
| Kumiko vs Xiaoyu | 17–13 | 56.67% |
| Kumiko vs Jack-8 | 17–12 | 58.62% |
| Kumiko vs Nina | 16–11 | 59.26% |
| Kumiko vs Leo | 13–12 | 52.00% |
| Kumiko vs Clive | 12–13 | 48.00% |
| Kumiko vs Feng | 13–10 | 56.52% |
| Kumiko vs Azucena | 10–13 | 43.48% |
| Kumiko vs Claudio | 8–13 | 38.10% |
| Kumiko vs Anna | 8–10 | 44.44% |
| Kumiko vs Lidia | 7–9 | 43.75% |
| Kumiko vs Zafina | 8–7 | 53.33% |
| Kumiko vs Alisa | 8–6 | 57.14% |
| Kumiko vs Kuma | 7–5 | 58.33% |
| Kumiko vs Fahkumram | 6–3 | 66.67% |
| Kumiko vs Eddy | 4–4 | 50.00% |
| Kumiko vs Shaheen | 3–3 | 50.00% |
| Kumiko vs Panda | 4–0 | 100.00% |
| Kumiko vs Raven | 2–2 | 50.00% |
| Kumiko vs Leroy | 0–2 | 0.00% |
Limitations
This data is often requested to give insight into which characters you have more trouble with than others, but it is not particularly helpful for that. The main issue is that it is heavily skewed by how strong the opponents you play are.
For example, this data suggests my worst matchup is clearly vs Reina, but that's just because most of those games are vs Yagami.
There is a way to account for this being worked on. The central idea is to assign each matchup a rating vs you which adjusts based on the result, much like the regular rating but also based on the rating of each player. With this, it would give a better summary of how well you perform vs each character.
In the meantime, this page is here to present the data as requested.