external benchmark
CUA-bench leaderboard
Vals CUA-bench. Every model the catalog carries a published CUA-bench value for, ranked by that value.
A Vals AI computer-use benchmark in which agents play six commercial video games with a keyboard and mouse.
The benchmark is defined by CUA-bench, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
About CUA-bench
What the benchmark measures and how its value is published, from the source’s own record.
What is CUA-bench?
CUA-bench (Vals CUA-bench) is an external benchmark published by CUA-bench. A Vals AI computer-use benchmark in which agents play six commercial video games with a keyboard and mouse. Its evaluation set is described by the source as six commercial video-game control tasks, including held-out games. The source rates its difficulty as keyboard-and-mouse computer use in real-time games.
How is CUA-bench scored?
Each model's result is published by CUA-bench as overall score with game-level task splits. 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.