Understand this story
Artificial Analysis has released AA-PersonalityBench, a benchmark for measuring the communication styles and personality traits of AI models. The benchmark uses an LLM judging panel to perform pairwise comparisons of answers to the same questions, covering 30 personality traits grouped into 8 indices: expressiveness, organization, informativeness, transparency, agreeableness, conviction, imagination, and Slop; it also programmatically measures 21 communication features such as answer length, structure, punctuation, and emphasis. Each trait has 30 questions, for a total of 900 questions; models answer without a system prompt, and results are presented as percentile rankings. Follow-up reports say Claude Fable 5.1 performed strongly on several indices, including expressiveness, informativeness, transparency, agreeableness, and assertiveness; Qwen3.8 27B averaged about 1,030 words per answer, nearly four times the 270 words of GPT-6 Luna.
AI-generated from public reports
Latest development · Report
Artificial Analysis releases AA-PersonalityBench to evaluate model personality and expression styleDevelopments
1 confirmed developments
- Source:Artificial Analysis (full article)
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 20
Artificial Analysis
Artificial Analysis releases AA-PersonalityBench to evaluate model personality and expression style
Artificial Analysis has released AA-PersonalityBench, using 900 curated questions to evaluate differences among language models across 30 personality traits and 21 communication characteristics. Personality traits are scored by LLM judges through pairwise comparisons and aggregated into eight indices: expressiveness, organization, informativeness, transparency, agreeableness, assertiveness, imaginativeness, and Slop; communication characteristics are computed programmatically across four categories of metrics: length, structure, punctuation, and emphasis. Results show that Claude Fable 5.1 stands out on multiple indices including expressiveness, informativeness, transparency, agreeableness, and assertiveness, while Qwen3.8 27B averages about 1,030 words per response, nearly four times the 270 words of GPT-6 Luna.
Oct 19
Full article from Artificial AnalysisFirst-party
Artificial Analysis Releases AA-PersonalityBench: Measuring AI Models' Communication Styles
Artificial Analysis launches AA-PersonalityBench, using an LLM jury to make pairwise comparisons of answers to the same questions, covering 30 personality traits grouped into 8 indices: Expressiveness, Organization, Informativeness, Transparency, Affinity, Conviction, Imagination, and Slop. The benchmark also programmatically measures 21 communication features, such as response length, structure, punctuation, and emphasis; each trait has 30 questions, for a total of 900 questions, and models answer without a system prompt, with results presented as percentile rankings.