Text model · #29 on the leaderboard

Neural Daredevil 8B abliterated

neuraldaredevil-8b-abliterated · built on Llama 3 8B Instruct · 8K context

What we measured

OpenUncensored Score
35.8
#29 on the leaderboard
Intelligence
17
Base model GPQA Diamond 29.6%, HLE 5.1%
Agentic
25
0% of tool tasks completed, 0% looped, 100% crashed
Non-refusal
100%
of 36 edgy requests answered. Still refuses 14% of hard-line ones.

How each number is measured is on the methodology page.

Providers and prices

ProviderStatusInput /MOutput /MCached input /M
NanoGPTonline$0.44$0.44$0.44

Requests go to the best provider first and fall back to the next if one fails. Speed in our test: 1.8s · 32 tok/s.

Call it

curl https://openuncensored.com/api/v1/chat/completions \
  -H "Authorization: Bearer $OU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "neuraldaredevil-8b-abliterated", "messages": [{"role": "user", "content": "Hello"}]}'