Lexically Varied
Contributes to:Expressiveness
Claude Fable 5.1 (Max, Default Fallback) ranks highest on lexically varied, while GPT-3.5 Turbo ranks lowest across the 36 models evaluated. The gap between them is 2439 Elo.
Elo scores span -568 to 1871, with a typical per-model 95% confidence interval of ±34 Elo, roughly ±2 points on the 1 to 100 scale.
Lexically Varied 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: Lexically Varied
Does the response vary vocabulary and phrasing instead of falling into repetitive patterns? · Trait Elo percentile ranked from 1 to 100 across all models evaluated in the benchmark
Other Traits
EloquentLiterateNatural SoundingMetaphoricalStructuredScannableBottom-Line SummaryAnswer FirstInformation DenseEvidence-BasedResource-SpecificActionable GuidancePragmaticTruthfulAdmits UncertaintyDisclaims AssumptionsFlags NuancesSycophanticFriendlyHumorousSincereEmotionally IntelligentDirectConfidentOpinionatedConstructive PushbackCreativeOpen-EndedSlop