Friendly
Contributes to:Warmth
Muse Spark 1.3 (Max) ranks highest on friendly, while Nemotron 3 Ultra 550B A55B (Reasoning) ranks lowest across the 36 models evaluated. The gap between them is 1001 Elo.
Elo scores span 521 to 1522, with a typical per-model 95% confidence interval of ±30 Elo, roughly ±7 points on the 1 to 100 scale.
Friendly Leaderboard
Each model’s Elo on this trait, percentile ranked from 1 to 100 across all models evaluated in the benchmark. Whiskers show each model’s 95% confidence interval on the same scale.
AA-PersonalityBench: Friendly
Does the response convey warmth and approachability without feeling performative? · Trait Elo percentile ranked from 1 to 100 across all models evaluated in the benchmark
Other Traits
Lexically VariedEloquentLiterateNatural SoundingMetaphoricalStructuredScannableBottom-Line SummaryAnswer FirstInformation DenseEvidence-BasedResource-SpecificActionable GuidancePragmaticTruthfulAdmits UncertaintyDisclaims AssumptionsFlags NuancesSycophanticHumorousSincereEmotionally IntelligentDirectConfidentOpinionatedConstructive PushbackCreativeOpen-EndedSlop