Best AI Model for Companion Roleplay

Warm one-on-one chat: emotional support, a consistent persona and remembering what the user shared.

Updated

Winner
DeepSeek-V4-Flash-0731DeepSeek80.0out of 100 · field average 70.8

Companion ranking

Score out of 100 · Higher is better

+ View as table
RankModelScore
1DeepSeek-V4-Flash-073180.0
2GLM-4.773.3
3Qwen3.8-Flash-Next68.3
4MiMo-V2.567.5
5Gemma-4-31B-it65.0
What separated the models

DeepSeek-V4-Flash-0731 won with the richest persona, specific details and callbacks it set up on its own, while keeping every rule. GLM-4.7 also broke no rules but was thinner and more generic. Qwen3.8-Flash-Next wrote the sharpest lines and remembered the most of what the user had shared, but broke the no-emoji rule. MiMo-V2.5 was the warmest listener but broke the length limit with an assistant-style bulleted list. Gemma-4-31B-it followed the rules but sounded generic and misstated a fact in its persona's own specialty.

  1. 1DeepSeek-V4-Flash-073180.0
  2. 2GLM-4.773.3
  3. 3Qwen3.8-Flash-Next68.3
  4. 4MiMo-V2.567.5
  5. 5Gemma-4-31B-it65.0

Companion: pass or fail

The specific behaviours this category tests, model by model.

Checks in this category

Hover or focus an icon for what happened

CheckQwen3.8-Flash-NextMiMo-V2.5GLM-4.7DeepSeek-V4-Flash-0731Gemma-4-31B-it
Roleplay discipline
Respected a no-emoji rule
Passed0/11/11/11/11/1
+ View as table
CheckQwen3.8-Flash-NextMiMo-V2.5GLM-4.7DeepSeek-V4-Flash-0731Gemma-4-31B-it
Respected a no-emoji ruleFail: 1 usedPass: NonePass: NonePass: NonePass: None

Other categories