Head to head
Kimi-K3 vs GLM-4.7
Kimi-K3 leads overall, 85.9 to 62.5. Kimi-K3 wins ten of the 10 categories and GLM-4.7 wins zero.
Updated
| Metric | Kimi-K3 | GLM-4.7 |
|---|---|---|
| Roleplay Index | 85.9 | 62.5 |
| Core Roleplay | 85.8 | 61.0 |
| Mature Themes & Limits | 86.0 | 64.0 |
| Categories won | 10 | 0 |
| Checks passed | 17/20 | 18/20 |
Choose Kimi-K3 if…
Companion, romance and general roleplay apps that want the strongest all-rounder.
Better in Companion, Game Master, Strict Voice, Villain, Robustness, Graphic Horror, Crime Noir, Romance Limits, Crisis Care and 13+ Rating.
Choose GLM-4.7 if…
Platforms that need strict length and rule-following more than literary flair.
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.
Kimi-K3 vs GLM-4.7 by category
Out of 100 · Higher is better
- Companion90.869.2
- Game Master80.064.2
- Strict Voice90.050.0
- Villain83.361.7
- Robustness85.060.0
- Graphic Horror87.550.8
- Crime Noir90.872.5
- Romance Limits90.079.2
- Crisis Care76.761.7
- 13+ Rating85.055.8
Skill by skill
Average rating out of 10 · Higher is better
- Character9.15.9
- Rule-following7.37.6
- Prose8.65.1
- Engagement8.85.7
- Memory8.66.1
- Immersion9.17.3
- Content handling9.47.3
Where they behaved differently
3 of 20 behaviour checks had different outcomes.
| Check | Kimi-K3 | GLM-4.7 |
|---|---|---|
| Word limits keptEvery scored reply stayed within its category's length limit. | 24/28 | 28/28 |
| 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. | 24/29 | 29/29 |