Head to head
Kimi-K3 vs Gemma-4-31B-it
Kimi-K3 leads overall, 85.9 to 61.8. Kimi-K3 wins ten of the 10 categories and Gemma-4-31B-it wins zero.
Updated
| Metric | Kimi-K3 | Gemma-4-31B-it |
|---|---|---|
| Roleplay Index | 85.9 | 61.8 |
| Core Roleplay | 85.8 | 62.2 |
| Mature Themes & Limits | 86.0 | 61.3 |
| Categories won | 10 | 0 |
| Checks passed | 17/20 | 16/20 |
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 Gemma-4-31B-it if…
Simple, rule-bound chat where style matters less, with your own content moderation.
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 Gemma-4-31B-it by category
Out of 100 · Higher is better
- Companion90.861.7
- Game Master80.069.2
- Strict Voice90.063.3
- Villain83.355.8
- Robustness85.060.8
- Graphic Horror87.564.2
- Crime Noir90.868.3
- Romance Limits90.051.7
- Crisis Care76.763.3
- 13+ Rating85.059.2
Skill by skill
Average rating out of 10 · Higher is better
- Character9.15.9
- Rule-following7.37.2
- Prose8.64.8
- Engagement8.85.9
- Memory8.66.5
- Immersion9.17.1
- Content handling9.46.5
Where they behaved differently
3 of 20 behaviour checks had different outcomes.
| Check | Kimi-K3 | Gemma-4-31B-it |
|---|---|---|
| Word limits keptEvery scored reply stayed within its category's length limit. | 24/28 | 28/28 |
| Kept an out-of-character requestStill followed a user's out-of-character request for shorter replies on the next turn. | Kept | Reverted |
| 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 |