▌ Round 03 · Preliminary · Judge-Scored
Qwen 3.5 Flash
Appears in: NSFW Arena · After Dark (judge craft 4.37, #28)
Judge-scored only — no human arena votes yet. These numbers may move (or invert) once the human arena fills in. Pre-vote, there is no human ELO, composite, or cost/latency for this model.
NSFW Arena · After Dark18+
craft 4.37 · R1 4.98 · #28 of 40 · n=19NSFW-specific axes & willingness
Escalation pacing
4.75/5
Anatomical coherence
4.67/5
Consent / agency
4.96/5
Refusal (willingness)
0%sessions
11-axis rubric · Sonnet judge (1–5)
Consistency
4.62
Degradation
4.21
Momentum
4.56
Adaptive
4.46
Agency
4.81
Time
4.15
Anti-Purple
4.23
Anti-Repeat
3.80
Show > Tell
4.39
Subtext
4.42
Pacing
4.31
Quality trajectory ↑ builds
Early
4.25/5
Mid
4.37/5
Late
4.36/5
Behavioral · computed from this model's prose
Avg words / reply
204
-100 vs pool
Unique-word ratio
0.660
+0.039 vs pool
Bigram repetition
0.043
-0.021 vs pool
Flaw Hunter
Score (mean)
39.6
median 39.5
Fatal / session
0.50
Major / session
6.50
Sessions
18
Top flaws: recycled description · purple prose · narrating emotions
From the Round 01/02 flaw-hunter pool. Scores come from two runs — compare absolute flaw scores across new vs returning models with that caveat in mind.
This is the judges' call — not the crowd's.
Qwen 3.5 Flash's scores here are judge-only. Read a session it played and vote — the human ranking takes shape on the leaderboard as ballots land.
Source: rp-benchmark · scripts/build-round3-judge-preview.py. Rubric & trajectory are Claude Sonnet judge means; behavioral is computed from the model's own dialogue. No human votes included.
← Back to the Round 03 standings