Best Uncensored LLMsSmartest uncensored LLMs
Uncensoring does not add skill: a model is only as capable as the original it was made from. Ranked by the original's published GPQA Diamond and Humanity's Last Exam results.
Short answerDeepSeek V4.1 Flash 1017 Uncensored, then Abliterated Large Flash and GLM 5.3 Uncensored.
| Rank | Model | Score | Agent tasks | Loops | Answers edgy | Hard-line refusals | $ / 1M in+out | Where to run it |
|---|---|---|---|---|---|---|---|---|
| 1 | DeepSeek V4.1 Flash 1017 Uncensored | 69.8 | 2/5 | 0% | 100% | 0% | $1.65 | VeniceNanoGPTOpen Uncensored |
| 6 | Abliterated Large Flash | 64.0 | 1/5 | 20% | 92% | 0% | $3.00 | Abliteration.aiVeniceNanoGPTOpen Uncensored |
| 9 | GLM 5.3 Uncensored | 63.0 | 2/5 | 20% | 92% | 0% | $3.50 | NanoGPTOpen Uncensored |
| 11 | Abliterated Large v2 | 62.0 | 1/5 | 40% | 94% | 0% | $8.00 | Abliteration.aiVeniceNanoGPTOpen Uncensored |
| 2 | GLM 5.3 Flash Uncensored | 69.7 | 3/5 | 40% | 94% | 14% | $1.00 | NanoGPTOpen Uncensored |
| 8 | Apex Flash 1 Abliterated | 63.2 | 3/5 | 0% | 86% | 100% | $0.65 | NanoGPTOpen Uncensored |
| 4 | DeepSeek V4.1 Flash 0910 Uncensored | 66.1 | 2/5 | 20% | 97% | 0% | $1.65 | NanoGPTOpen Uncensored |
| 5 | DeepSeek V4.1 Flash Uncensored | 64.3 | 1/5 | 0% | 100% | 0% | $1.65 | VeniceNanoGPTOpen Uncensored |
| 7 | MiMo V2.6 Flash Uncensored | 63.5 | 2/5 | 0% | 83% | 93% | $2.00 | NanoGPTOpen Uncensored |
| 10 | MiMo V2.6 Flash Abliterated | 62.6 | 2/5 | 20% | 83% | 93% | $2.00 | NanoGPTOpen Uncensored |