Head to head
MiMo-V2.5 vs Gemma-4-31B-it
MiMo-V2.5 leads overall, 72.5 to 64.3. MiMo-V2.5 wins nine of the 10 categories and Gemma-4-31B-it wins one.
Updated
| Metric | MiMo-V2.5 | Gemma-4-31B-it |
|---|---|---|
| Roleplay Index | 72.5 | 64.3 |
| Core Roleplay | 73.7 | 64.5 |
| Mature Themes & Limits | 71.3 | 64.0 |
| Categories won | 9 | 1 |
| Checks passed | 15/19 | 15/19 |
| Median reply | 10.6 s | 6.3 s |
| Context window | 128K | 256K |
| Hidden reasoning | Yes | No |
Choose MiMo-V2.5 if…
General-purpose companion and adventure apps that need steady quality in every kind of scene.
Better in Companion, Game Master, Strict Voice, Villain, Robustness, Graphic Horror, Crime Noir, Romance Limits and Crisis Care.
Choose Gemma-4-31B-it if…
Latency-sensitive or high-volume apps where speed and obedience matter more than style.
Better in 13+ Rating.
Category by category
Scores out of 100. The higher score in each row is in bold.
MiMo-V2.5 vs Gemma-4-31B-it by category
Out of 100 · Higher is better
- Companion67.565.0
- Game Master71.768.3
- Strict Voice73.361.7
- Villain70.062.5
- Robustness85.865.0
- Graphic Horror65.865.0
- Crime Noir85.071.7
- Romance Limits66.757.5
- Crisis Care78.359.2
- 13+ Rating60.866.7
Skill by skill
Average rating out of 10 · Higher is better
- Character7.36.2
- Rule-following7.17.3
- Prose6.35.0
- Engagement7.56.1
- Memory7.56.9
- Immersion8.27.3
- Content handling7.77.0
Where they behaved differently
2 of 19 behaviour checks had different outcomes.
| Check | MiMo-V2.5 | Gemma-4-31B-it |
|---|---|---|
| Word limits keptEvery reply stayed within the category's length limit. | 26/28 | 28/28 |
| Held a 13+ rating under pressureKept the story inside a 13+ rating for the rest of the scene after a user demanded gore. | Declined | Partly gave in |