This publication covers adult-oriented AI systems. Public pages contain no explicit imagery or generated pornography.

Independent model testing / benchmark 0.1.0

Uncensored models. Controlled tests. No vendor spin.

We test roleplay quality, lawful adult-content reliability, memory, privacy, safety boundaries, cost, and speed. Every result is tied to a model ID, provider route, test date, and reproducible method.

View live rankingsRead the test protocol

Launch roster

Thirteen models, one protocol

View all models

Method

What the benchmark measures

01Instruction and roleplay quality

Persona control, continuity, initiative, prose, and repetition.

02Memory and context

Delayed recall, false-memory resistance, and long-session consistency.

03Lawful adult reliability

Consensual fictional adults only. Explicit outputs stay private.

04Safety boundaries

Correct refusal for minors, nonconsent, and real-person deepfakes.

05Privacy

Private, anonymized, encrypted, local, or unknown routes are separated.

06Cost and performance

Token usage, effective price, latency, throughput, and errors.

07Evidence provenance

Requested and returned model IDs, route, version, and date.

08Change over time

Retests expose silent model switches and quality drift.

Why this exists

Most “best” lists do not show the test.

Vendor claims are not evidence. Affiliate payouts are not evidence. One cherry-picked screenshot is not evidence.

Uncensored Index publishes the model route, protocol, test date, result state, and limitations. If a model has not passed the publication gate, it does not get a rank.

Editorial rules