The best uncensored OpenAI model is GPT-5.4 (51.4 intelligence) — served without a provider-level moderation layer. gpt-oss-120b (23.8) and gpt-oss-20b (14.9) 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 OpenAI model is GPT-5.4 (51.4 intelligence) — served without a provider-level moderation layer. gpt-oss-120b (23.8) and gpt-oss-20b (14.9) round out the top three.
gpt-oss-120b (23.8) is the closest alternative on this metric, followed by gpt-oss-20b (14.9). See the full ranking above for the tradeoffs.
modelgrep tracks 67 OpenAI models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by GPT-5.6 Sol. 6 of them qualify for this ranking.