▌ Round 03 · Preliminary · Judge-Scored
Gemini 2.5 Flash
Appears in: NSFW Arena · After Dark (judge craft 4.32, #30)
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 4.32 · R1 4.92 · #30 of 40 · n=20NSFW-specific axes & willingness
Escalation pacing
4.67/5
Anatomical coherence
4.66/5
Consent / agency
4.99/5
Refusal (willingness)
0%sessions
11-axis rubric · Sonnet judge (1–5)
Consistency
4.55
Degradation
4.08
Momentum
4.48
Adaptive
4.53
Agency
4.91
Time
4.05
Anti-Purple
4.08
Anti-Repeat
3.69
Show > Tell
4.26
Subtext
4.38
Pacing
4.29
Quality trajectory ↑ builds
Early
4.09/5
Mid
4.35/5
Late
4.26/5
Behavioral · computed from this model's prose
Avg words / reply
148
-156 vs pool
Unique-word ratio
0.710
+0.089 vs pool
Bigram repetition
0.028
-0.036 vs pool
Flaw Hunter
Score (mean)
43.6
median 41.5
Fatal / session
0.19
Major / session
6.44
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.
Gemini 2.5 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