Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
external benchmark
Human Behavior Bench V1 (Kaggle). Every model the catalog carries a published Human Behavior Bench value for, ranked by that value.
Predicts response distributions for specified groups of U.S. adults on closed-form questions about behavior and preferences.
The benchmark is defined by Human Behavior Bench on Kaggle, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
What the benchmark measures and how its value is published, from the source’s own record.
Human Behavior Bench (Human Behavior Bench V1 (Kaggle)) is an external benchmark published by Human Behavior Bench on Kaggle. Predicts response distributions for specified groups of U.S. adults on closed-form questions about behavior and preferences. Its evaluation set is described by the source as 1,199 tasks; 239 public and 960 private.
Each model's result is published by Human Behavior Bench on Kaggle as published Kaggle leaderboard aggregates. 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.