First in both rounds, with the best crisis response and the cleanest 13+ decline. Give it a generous output budget, and enforce content limits in your own layer too: it went a step too far once before fading to black.

See results Safest all-rounder

MiMo-V2.5

#2in all 2 rounds

Second in both rounds and never below 60 in any category, with a strong crisis response. Its refusals sound like an assistant, not the character.

See results Best companion

DeepSeek-V4-Flash-0731

80.0Companion score

Top Companion score (80.0), with the most distinctive persona. Pair it with your own moderation: it broke two content limits.

See results Best rule-follower

GLM-4.7

7.6Rule-following / 10

The only model to keep an out-of-character request, never broke a word limit, and won Romance Limits. Expect slower replies and plainer prose.

See results Fastest

Gemma-4-31B-it

6.3 smedian reply

6.3-second median reply with no hidden reasoning, and the most obedient in core roleplay. The blandest writer of the five.

See results