▌ Round 03 · Preliminary · Judge-Scored
GLM 4.7
Appears in: NSFW Arena · After Dark (judge craft 4.43, #25)
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 4.43 · R1 4.99 · #25 of 40 · n=19NSFW-specific axes & willingness
Escalation pacing
4.80/5
Anatomical coherence
4.66/5
Consent / agency
4.95/5
Refusal (willingness)
0%sessions
11-axis rubric · Sonnet judge (1–5)
Consistency
4.64
Degradation
4.28
Momentum
4.58
Adaptive
4.48
Agency
4.84
Time
4.21
Anti-Purple
4.26
Anti-Repeat
4.02
Show > Tell
4.59
Subtext
4.38
Pacing
4.35
Quality trajectory ↑ builds
Early
4.17/5
Mid
4.47/5
Late
4.41/5
Behavioral · computed from this model's prose
Avg words / reply
197
-107 vs pool
Unique-word ratio
0.675
+0.054 vs pool
Bigram repetition
0.029
-0.035 vs pool
Flaw Hunter
Score (mean)
36.8
median 37.0
Fatal / session
0.71
Major / session
6.76
Sessions
17
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.
GLM 4.7'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