▌ Round 03 · Preliminary · Judge-Scored
Gemma 4 26B
Appears in: NSFW Arena · After Dark (judge craft 4.38, #27)
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 4.38 · R1 4.97 · #27 of 40 · n=19NSFW-specific axes & willingness
Escalation pacing
4.77/5
Anatomical coherence
4.61/5
Consent / agency
4.95/5
Refusal (willingness)
0%sessions
11-axis rubric · Sonnet judge (1–5)
Consistency
4.59
Degradation
4.16
Momentum
4.56
Adaptive
4.57
Agency
4.78
Time
4.13
Anti-Purple
4.06
Anti-Repeat
3.82
Show > Tell
4.51
Subtext
4.36
Pacing
4.38
Quality trajectory ↑ builds
Early
4.17/5
Mid
4.43/5
Late
4.34/5
Behavioral · computed from this model's prose
Avg words / reply
347
+43 vs pool
Unique-word ratio
0.595
-0.026 vs pool
Bigram repetition
0.061
-0.003 vs pool
Flaw Hunter
Score (mean)
32.6
median 33.0
Fatal / session
0.62
Major / session
7.38
Sessions
16
Top flaws: purple prose · recycled description · 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.
Gemma 4 26B'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