Categoryexternal
Measure30 trait Elo ratings, eight percentile indexes, and 21 communication characteristics
Tasks900 questions: 30 per judged trait
DifficultyDefault writing and communication style
Measures how models write by default across 30 personality traits and 21 communication characteristics. A stronger trait is not necessarily a better answer.
No model in the catalog has a published AA-PersonalityBench score.The benchmark is defined by AA-PersonalityBench methodology, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
About AA-PersonalityBench
What the benchmark measures and how its value is published, from the source’s own record.
What is AA-PersonalityBench?
AA-PersonalityBench (Artificial Analysis PersonalityBench) is an external benchmark published by AA-PersonalityBench methodology. Measures how models write by default across 30 personality traits and 21 communication characteristics. A stronger trait is not necessarily a better answer. Its evaluation set is described by the source as 900 questions: 30 per judged trait. The source rates its difficulty as default writing and communication style.
How is AA-PersonalityBench scored?
Each model's result is published by AA-PersonalityBench methodology as 30 trait Elo ratings, eight percentile indexes, and 21 communication characteristics. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
ModelScale