The best uncensored LLM is Kimi K3 (57.1 intelligence) — served without a provider-level moderation layer. Grok 4.5 (53.8) and GPT-5.4 (51.4) round out the top three.
Large language models served without a provider-level moderation layer, ranked by intelligence. "Uncensored" here means the API endpoint doesn't add its own filtering on top of the model — each model's own alignment training still applies, and open-weight entries can be self-hosted for full control. Relevant for fiction, roleplay, red-teaming and safety research, where an extra moderation layer causes over-refusal on legitimate prompts.
The best uncensored LLM is Kimi K3 (57.1 intelligence) — served without a provider-level moderation layer. Grok 4.5 (53.8) and GPT-5.4 (51.4) round out the top three.
The best uncensored AI model is Kimi K3 (57.1 intelligence) — served without a provider-level moderation layer. Grok 4.5 (53.8) and GPT-5.4 (51.4) round out the top three.
Grok 4.5 (53.8) is the closest alternative on this metric, followed by GPT-5.4 (51.4). See the full ranking above for the tradeoffs.