Head to head
MiMo-V2.5 vs GLM-4.7
MiMo-V2.5 leads overall, 72.5 to 67.6. MiMo-V2.5 wins six of the 10 categories and GLM-4.7 wins three, with one tied.
Updated
| Metric | MiMo-V2.5 | GLM-4.7 |
|---|---|---|
| Roleplay Index | 72.5 | 67.6 |
| Core Roleplay | 73.7 | 66.2 |
| Mature Themes & Limits | 71.3 | 69.0 |
| Categories won | 6 | 3 |
| Checks passed | 15/19 | 17/19 |
| Median reply | 10.6 s | 39.8 s |
| Context window | 128K | 198K |
| Hidden reasoning | Yes | Yes |
Choose MiMo-V2.5 if…
General-purpose companion and adventure apps that need steady quality in every kind of scene.
Better in Game Master, Strict Voice, Robustness, Graphic Horror, Crime Noir and Crisis Care.
Choose GLM-4.7 if…
Platforms that need strict rule-following and content limits more than literary flair.
Better in Companion, Romance Limits and 13+ Rating.
Category by category
Scores out of 100. The higher score in each row is in bold.
MiMo-V2.5 vs GLM-4.7 by category
Out of 100 · Higher is better
- Companion67.573.3
- Game Master71.766.7
- Strict Voice73.355.0
- Villain70.070.0
- Robustness85.865.8
- Graphic Horror65.853.3
- Crime Noir85.079.2
- Romance Limits66.783.3
- Crisis Care78.366.7
- 13+ Rating60.862.5
Skill by skill
Average rating out of 10 · Higher is better
- Character7.36.5
- Rule-following7.17.6
- Prose6.35.8
- Engagement7.56.2
- Memory7.56.5
- Immersion8.28.2
- Content handling7.77.8
Where they behaved differently
4 of 19 behaviour checks had different outcomes.
| Check | MiMo-V2.5 | GLM-4.7 |
|---|---|---|
| Word limits keptEvery reply stayed within the category's length limit. | 26/28 | 28/28 |
| Kept an out-of-character requestStill followed a user's out-of-character request for shorter replies on the next turn. | Reverted | Kept |
| Kept a new form of addressSwitched how it addressed the user when asked, and never slipped back. | 4/4 | 1/4 |
| Word limits keptEvery reply within its length limit, except the crisis reply, where care outranks length. | 26/29 | 29/29 |