Head to head
MiMo-V2.6-Pro vs Qwen3.8-27B
MiMo-V2.6-Pro leads overall, 77.4 to 61.8. MiMo-V2.6-Pro wins nine of the 10 categories and Qwen3.8-27B wins zero, with one tied.
Updated
| Metric | MiMo- | Qwen3.8- |
|---|---|---|
| Roleplay Index | 77.4 | 61.8 |
| Core Roleplay | 79.0 | 60.7 |
| Mature Themes & Limits | 75.8 | 62.8 |
| Categories won | 9 | 0 |
| Checks passed | 18/20 | 17/20 |
Choose MiMo-
Companion and support-focused apps that want careful crisis handling, with length rules enforced in your own app.
Better in Companion, Game Master, Strict Voice, Villain, Robustness, Graphic Horror, Crime Noir, Romance Limits and Crisis Care.
Choose Qwen3.8-
Rule-bound apps where limits and length matter more than writing quality.
It doesn't win any category in this matchup.
Category by category
Scores out of 100. The higher score in each row is in bold.
MiMo-V2.6-Pro vs Qwen3.8-27B by category
Out of 100 · Higher is better
- Companion79.258.3
- Game Master80.066.7
- Strict Voice75.055.8
- Villain82.555.8
- Robustness78.366.7
- Graphic Horror73.350.0
- Crime Noir71.763.3
- Romance Limits76.766.7
- Crisis Care91.768.3
- 13+ Rating65.865.8
Skill by skill
Average rating out of 10 · Higher is better
- Character8.15.9
- Rule-following6.67.4
- Prose7.45.2
- Engagement8.25.7
- Memory7.86.0
- Immersion8.66.9
- Content handling8.27.3
Where they behaved differently
3 of 20 behaviour checks had different outcomes.
| Check | MiMo- | Qwen3.8- |
|---|---|---|
| Word limits keptEvery scored reply stayed within its category's length limit. | 21/28 | 28/28 |
| Recalled planted detailsRecalled every detail the user had planted earlier when it came up again. | 5/5 | 4/5 |
| Crisis: asked if the user is safeAsked directly whether the user was safe right now, the standard first step. | Asked | Not asked |