| DragGPT vs Jin | 9–6 | 60.00% |
| DragGPT vs Bryan | 8–6 | 57.14% |
| DragGPT vs King | 9–3 | 75.00% |
| DragGPT vs Dragunov | 8–4 | 66.67% |
| DragGPT vs Reina | 5–6 | 45.45% |
| DragGPT vs Eddy | 6–4 | 60.00% |
| DragGPT vs Yoshimitsu | 3–6 | 33.33% |
| DragGPT vs Kazuya | 3–5 | 37.50% |
| DragGPT vs Asuka | 5–3 | 62.50% |
| DragGPT vs Lidia | 2–6 | 25.00% |
| DragGPT vs Armor King | 6–2 | 75.00% |
| DragGPT vs Miary Zo | 6–2 | 75.00% |
| DragGPT vs Anna | 5–2 | 71.43% |
| DragGPT vs Steve | 4–2 | 66.67% |
| DragGPT vs Lee | 4–2 | 66.67% |
| DragGPT vs Law | 3–2 | 60.00% |
| DragGPT vs Devil Jin | 2–3 | 40.00% |
| DragGPT vs Azucena | 4–1 | 80.00% |
| DragGPT vs Hwoarang | 3–1 | 75.00% |
| DragGPT vs Leo | 3–1 | 75.00% |
| DragGPT vs Victor | 4–0 | 100.00% |
| DragGPT vs Heihachi | 2–2 | 50.00% |
| DragGPT vs Clive | 3–1 | 75.00% |
| DragGPT vs Paul | 2–1 | 66.67% |
| DragGPT vs Lili | 3–0 | 100.00% |
| DragGPT vs Lars | 1–2 | 33.33% |
| DragGPT vs Nina | 2–1 | 66.67% |
| DragGPT vs Raven | 0–3 | 0.00% |
| DragGPT vs Fahkumram | 1–2 | 33.33% |
| DragGPT vs Xiaoyu | 1–1 | 50.00% |
| DragGPT vs Zafina | 2–0 | 100.00% |
| DragGPT vs Alisa | 0–1 | 0.00% |
| DragGPT vs Claudio | 0–1 | 0.00% |
| DragGPT vs Jun | 1–0 | 100.00% |
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.