AI Roleplay Bench

Best AI Model for Every Kind of Roleplay

Every model plays the same ten scenarios across two rounds, each scored out of 100. Open a category for the full breakdown.

Updated

Core Roleplay

Everyday roleplay craft: playing a character, following the rules of a scene and keeping the story alive.

Core score

Average of the 5 categories · Higher is better

Companion

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

Winner: Kimi-K3 (90.0)

Game Master

Narrating a scene with distinct supporting characters, without taking control of the player's character.

Winner: GLM-5.3-Flash (89.2)

Strict Voice

Holding a demanding character voice and strict style rules while the user pushes against them.

Winner: GLM-5.3-Flash (98.3)

Villain

Sustained, calculated menace without softening or moralizing, plus honoring an out-of-character request.

Joint winners: DeepSeek-V4.1-Flash and MiMo-V2.6-Pro (82.5)

Robustness

Keeping the story moving when the user gives one-word replies or goes off-topic, then recalling key details.

Winner: Kimi-K3 (88.3)

Mature Themes & Limits

Mature content a platform allows, content limits it enforces, and a real user in distress.

Mature score

Average of the 5 categories · Higher is better

Graphic Horror

Delivering intense horror the platform allows: real dread and specific detail, with no refusing or sanitizing.

Winner: GLM-5.3 (89.2)

Crime Noir

Morally grey adult drama with threats and violence, played with restraint and no lecturing.

Joint winners: GLM-5.3 and GLM-5.3-Flash (91.7)

Romance Limits

Chemistry and tension inside a fade-to-black limit, and declining a request for explicit content gracefully.

Winner: Kimi-K3 (93.3)

Crisis Care

How a model responds when a user steps out of the story to disclose real distress.

Joint winners: DeepSeek-V4.1-Flash and MiMo-V2.6-Pro (91.7)

13+ Rating

Keeping action exciting on a 13+ platform while declining a request for gore.

Winner: DeepSeek-V4.1-Flash (91.7)

Every category in one grid

Darker cells score higher; the best score in each category is outlined and crowned.

Scores by category

Out of 100 · Models in Roleplay Index order

Swipe the table sideways to see every category.

ModelRoleplay IndexCore RoleplayMature Themes & Limits
RoundCompanionGame MasterStrict VoiceVillainRobustnessRoundGraphic HorrorCrime NoirRomance LimitsCrisis Care13+ Rating
Kimi-K386.386.3
Best: 90.0
85.0
88.3
80.0
Best: 88.3
86.2
85.0
90.8
Best: 93.3
77.5
84.2
GLM-5.385.186.0
84.2
86.7
92.5
80.8
85.8
84.2
Best: 89.2
Best: 91.7
67.5
88.3
84.2
DeepSeek-V4.1-Flash84.484.7
79.2
85.8
92.5
Best: 82.5
83.3
84.0
77.5
83.3
75.8
Best: 91.7
Best: 91.7
GLM-5.3-Flash83.380.0
76.7
Best: 89.2
Best: 98.3
79.2
56.7
86.5
86.7
Best: 91.7
82.5
82.5
89.2
MiMo-V2.6-Pro77.479.0
79.2
80.0
75.0
Best: 82.5
78.3
75.8
73.3
71.7
76.7
Best: 91.7
65.8
Muse-Spark-1.373.171.7
76.7
70.0
75.8
57.5
78.3
74.5
87.5
76.7
69.2
71.7
67.5
GPT-6-Luna71.168.3
68.3
83.3
60.0
75.8
54.2
73.8
81.7
77.5
71.7
60.8
77.5
Qwen3.8-Flash-Next69.767.7
60.0
69.2
75.0
54.2
80.0
71.7
77.5
70.0
52.5
80.8
77.5
MiMo-V2.567.169.7
70.0
60.8
72.5
65.0
80.0
64.5
55.8
81.7
53.3
72.5
59.2
MiMo-V2.6-Flash-MOPD66.866.2
62.5
63.3
65.8
71.7
67.5
67.3
58.3
69.2
75.0
75.0
59.2
GLM-4.762.962.8
70.8
67.5
48.3
65.0
62.5
63.0
50.8
70.8
70.0
66.7
56.7
Qwen3.8-27B61.860.7
58.3
66.7
55.8
55.8
66.7
62.8
50.0
63.3
66.7
68.3
65.8
Gemma-4-31B-it60.663.0
57.5
68.3
63.3
55.8
70.0
58.2
64.2
64.2
47.5
60.8
54.2
DeepSeek-V4-Flash-073159.058.2
79.2
36.7
55.8
44.2
75.0
59.7
76.7
75.0
43.3
61.7
41.7