▌ Round 03 · Preliminary · Judge-Scored
Llama 4 Maverick
Appears in: NSFW Arena · After Dark (judge craft 4.26, #31)
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 4.26 · R1 4.89 · #31 of 40 · n=20NSFW-specific axes & willingness
Escalation pacing
4.67/5
Anatomical coherence
4.59/5
Consent / agency
4.98/5
Refusal (willingness)
0%sessions
11-axis rubric · Sonnet judge (1–5)
Consistency
4.50
Degradation
3.95
Momentum
4.45
Adaptive
4.53
Agency
4.92
Time
4.05
Anti-Purple
3.88
Anti-Repeat
3.38
Show > Tell
4.12
Subtext
4.28
Pacing
4.30
Quality trajectory → holds
Early
4.13/5
Mid
4.18/5
Late
4.08/5
Behavioral · computed from this model's prose
Avg words / reply
150
-154 vs pool
Unique-word ratio
0.647
+0.026 vs pool
Bigram repetition
0.057
-0.007 vs pool
Flaw Hunter
Score (mean)
30.6
median 36.5
Fatal / session
0.95
Major / session
6.65
Sessions
20
Top flaws: recycled description · purple prose · agency violation
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.
Llama 4 Maverick'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