Categoryexternal
MeasureAccuracy, cost per test and duration
TasksAbout 1,250 agentic tasks
DifficultyLong tool-using agent work in finance, coding, law and tax
Vals AI comparison of model routers with single models on long agentic work in finance, coding, law and tax, using the same agents, tasks and graders as the Vals Index.
No model in the catalog has a published Vals Router Index score.The benchmark is defined by Vals Router 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.
About Vals Router Index
What the benchmark measures and how its value is published, from the source’s own record.
What is Vals Router Index?
Vals Router Index (Vals Router Index (Vals AI)) is an external benchmark published by Vals Router Index leaderboard and methodology. Vals AI comparison of model routers with single models on long agentic work in finance, coding, law and tax, using the same agents, tasks and graders as the Vals Index. Its evaluation set is described by the source as about 1,250 agentic tasks. The source rates its difficulty as long tool-using agent work in finance, coding, law and tax.
How is Vals Router Index scored?
Each model's result is published by Vals Router Index leaderboard and methodology as accuracy, cost per test and duration. 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.
ModelScale