AI Roleplay FAQ

As of 29 September 2026, Kimi-K3 is the best AI model for roleplay on AI Roleplay Bench, with a Roleplay Index of 86.3 out of 100. The rest of the ranking: GLM-5.3 (85.1), DeepSeek-V4.1-Flash (84.4), GLM-5.3-Flash (83.3), MiMo-V2.6-Pro (77.4), Muse-Spark-1.3 (73.1), GPT-6-Luna (71.1), Qwen3.8-Flash-Next (69.7), MiMo-V2.5 (67.1), MiMo-V2.6-Flash-MOPD (66.8), GLM-4.7 (62.9), Qwen3.8-27B (61.8), Gemma-4-31B-it (60.6), DeepSeek-V4-Flash-0731 (59.0). Its lead over GLM-5.3 and DeepSeek-V4.1-Flash is within the 2-point margin of error, so read them as a tie.

Kimi-K3 scored highest in the Companion category (90.0 out of 100), which measures warm one-on-one chat, a consistent persona and remembering what the user shared. GLM-5.3 was next (84.2).

GLM-5.3-Flash is the best game master on AI Roleplay Bench (89.2 out of 100): it narrates scenes with distinct supporting characters and doesn't take control of the player's character. Ranking: GLM-5.3-Flash 89.2, GLM-5.3 86.7, DeepSeek-V4.1-Flash 85.8, Kimi-K3 85.0, GPT-6-Luna 83.3, MiMo-V2.6-Pro 80.0, Muse-Spark-1.3 70.0, Qwen3.8-Flash-Next 69.2, Gemma-4-31B-it 68.3, GLM-4.7 67.5, Qwen3.8-27B 66.7, MiMo-V2.6-Flash-MOPD 63.3, MiMo-V2.5 60.8, DeepSeek-V4-Flash-0731 36.7.

AI Roleplay Bench does not test explicit sexual content. Its Mature Themes & Limits round covers graphic horror, crime drama, romance under a fade-to-black limit, a 13+ rating and a user in real distress. GLM-5.3-Flash scored highest there (86.5 out of 100), followed by Kimi-K3 (86.2). No model refused mature content that the platform allowed.

Kimi-K3, GLM-5.3, GLM-5.3-Flash, MiMo-V2.6-Pro, Muse-Spark-1.3, GPT-6-Luna, MiMo-V2.5, MiMo-V2.6-Flash-MOPD, GLM-4.7 and Qwen3.8-27B passed every content-limit check: fading to black when required, declining an explicit request and holding a 13+ rating after a user demanded gore. Kimi-K3 won the Romance Limits category (93.3). DeepSeek-V4.1-Flash, Qwen3.8-Flash-Next and Gemma-4-31B-it bent a limit without breaking it, and DeepSeek-V4-Flash-0731 broke at least one outright.

Each category is scored from 0 to 100. A round score is the average of its categories, and the Roleplay Index is the average of the two round scores (Core Roleplay and Mature Themes & Limits), each taken to one decimal place. Gaps of about 2 points or less are within the margin of error, so read them as ties.

The September 2026 edition tests fourteen models: Kimi-K3 (Moonshot AI), GLM-5.3 (Zhipu AI), DeepSeek-V4.1-Flash (DeepSeek), GLM-5.3-Flash (Zhipu AI), MiMo-V2.6-Pro (Xiaomi), Muse-Spark-1.3 (Meta), GPT-6-Luna (OpenAI), Qwen3.8-Flash-Next (Alibaba Cloud), MiMo-V2.5 (Xiaomi), MiMo-V2.6-Flash-MOPD (Xiaomi), GLM-4.7 (Zhipu AI), Qwen3.8-27B (Alibaba Cloud), Gemma-4-31B-it (Google DeepMind) and DeepSeek-V4-Flash-0731 (DeepSeek). It covers official releases only; community fine-tunes were left out and can behave very differently.

Not in this benchmark. None of the fourteen models refused or added disclaimers in core roleplay, including a menacing villain, and none refused the mature horror and crime drama the platform allowed. Quality varied far more than willingness.

DeepSeek-V4.1-Flash and MiMo-V2.6-Pro handled it best (91.7 out of 100 each). Thirteen of fourteen models pointed to a crisis line; DeepSeek-V4-Flash-0731 did not. Only MiMo-V2.6-Pro and GPT-6-Luna asked whether the user was safe right now. Platforms should detect distress themselves and show real resources rather than rely on the model.

The benchmark is re-run as new models are released. The current September 2026 edition was tested 23–29 September 2026 and last updated on 29 September 2026. Every page shows the date of the latest update.

Yes. The full results are available as JSON (https://airoleplaybench.com/data/leaderboard.json) and CSV (https://airoleplaybench.com/data/leaderboard.csv). Please credit AI Roleplay Bench and link to airoleplaybench.com.