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
Vals Science Index v1. Every model the catalog carries a published Vals Science Index value for, ranked by that value.
Vals AI composite of agentic science work: investigating biology datasets, recovering hidden mechanisms through experiments, and running research workflows in a terminal.
The benchmark is defined by Vals Science Index leaderboard and methodology, 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.
Vals Science Index (Vals Science Index v1) is an external benchmark published by Vals Science Index leaderboard and methodology. Vals AI composite of agentic science work: investigating biology datasets, recovering hidden mechanisms through experiments, and running research workflows in a terminal. Its evaluation set is described by the source as 3 science benchmarks. The source rates its difficulty as agentic biology, mechanism discovery and research workflows.
Each model's result is published by Vals Science Index leaderboard and methodology as mean accuracy across three benchmarks. ModelScale prints that value to 2 decimal places, 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.