Current
September 2026 edition
Fourteen models, ten roleplay categories and 840 scored replies across two rounds: core roleplay craft, and mature themes with platform content limits.
- 29 September 2026: Added three models: MiMo-V2.6-Pro, Muse-Spark-1.3 and GPT-6-Luna. All fourteen were judged together, so every score changed.
- 28 September 2026: Added six models: Kimi-K3, GLM-5.3, DeepSeek-V4.1-Flash, GLM-5.3-Flash, MiMo-V2.6-Flash-MOPD and Qwen3.8-27B. All eleven were judged together, so the scores of the first five changed too. Reply speed is no longer reported, because it depends mostly on the provider and its load, not on the model.
- 25 September 2026: First published with five models: Qwen3.8-Flash-Next, MiMo-V2.5, GLM-4.7, DeepSeek-V4-Flash-0731 and Gemma-4-31B-it.
Tested 23–29 September 2026 · 840 scored replies