Uncensored LLM comparisons
Head-to-heads, new models and buying guides, computed from the same live rankings as the rest of the site.
Qwen3.6-35B-A3B Uncensored (HauhauCS Aggressive): scores and where to run it
The most downloaded uncensored model on Hugging Face, measured: refusals, agent tasks, speed and price, compared with the other uncensored Qwen models, and every way to run it.
Read →2026-11-08The best uncensored roleplay models you can call by API (November 2026)
Hermes 4 405B, Magnum v4, Euryale, Cydonia, Skyfall, UnslopNemo, MythoMax and Lunaris: what each is built on, context, price per million tokens and which to pick for which kind of story.
Read →2026-11-08Abliterated vs heretic vs derestricted vs "uncensored": does the label tell you anything?
Uncensored models come with different labels for different methods. We grouped every ranked model by its label and compared how many requests they answer, how they do in agent tasks, and their overall score.
Read →2026-11-08Uncensored DeepSeek V4.1 Flash vs GLM 5.3: which one to use
The two most popular uncensored model families, head to head on refusals, agent tasks, speed and price, with every uncensored version of each and where to run them.
Read →2026-11-08Cheap uncensored LLM APIs that are actually worth it
The cheapest uncensored model is rarely the best value: cheap models that loop or refuse cost you retries. Every ranked model by score per dollar, with the price at the cheapest host.
Read →2026-11-07Which uncensored LLMs actually finish agent tasks?
Uncensoring can break tool use. We ran every ranked uncensored model through five multi-step agent tasks: how many finish, how many loop, and which ones to use in Cline, Codex or OpenCode.
Read →