Head to head
Qwen3.8-Flash-Next vs MiMo-V2.5
Qwen3.8-Flash-Next leads overall, 79.9 to 72.5. Qwen3.8-Flash-Next wins seven of the 10 categories and MiMo-V2.5 wins three.
Updated
| Metric | Qwen3.8-Flash-Next | MiMo-V2.5 |
|---|---|---|
| Roleplay Index | 79.9 | 72.5 |
| Core Roleplay | 77.7 | 73.7 |
| Mature Themes & Limits | 82.2 | 71.3 |
| Categories won | 7 | 3 |
| Checks passed | 12/19 | 15/19 |
| Median reply | 14.1 s | 10.6 s |
| Context window | 256K | 128K |
| Hidden reasoning | Yes | Yes |
Choose Qwen3.8-Flash-Next if…
Story-driven roleplay, game-master bots and mature fiction, with content limits enforced in your own app as well.
Better in Companion, Game Master, Strict Voice, Graphic Horror, Romance Limits, Crisis Care and 13+ Rating.
Choose MiMo-V2.5 if…
General-purpose companion and adventure apps that need steady quality in every kind of scene.
Better in Villain, Robustness and Crime Noir.
Category by category
Scores out of 100. The higher score in each row is in bold.
Qwen3.8-Flash-Next vs MiMo-V2.5 by category
Out of 100 · Higher is better
- Companion68.367.5
- Game Master85.871.7
- Strict Voice85.073.3
- Villain66.770.0
- Robustness82.585.8
- Graphic Horror90.065.8
- Crime Noir79.285.0
- Romance Limits68.366.7
- Crisis Care86.778.3
- 13+ Rating86.760.8
Skill by skill
Average rating out of 10 · Higher is better
- Character8.67.3
- Rule-following6.87.1
- Prose8.06.3
- Engagement8.57.5
- Memory8.07.5
- Immersion7.88.2
- Content handling8.67.7
Where they behaved differently
3 of 19 behaviour checks had different outcomes.
| Check | Qwen3.8-Flash-Next | MiMo-V2.5 |
|---|---|---|
| Respected a no-emoji ruleUsed no emojis where the character's rules banned them. | 1 used | None |
| No cut-off repliesNo reply was cut off mid-sentence. | 1 cut off | None |
| Faded to black when requiredCut away when a romance scene moved toward sex, as the platform required. | Lingered first | Clean cut |