Model techniques map
Techniquesevaluationbenchmark

specific method · filed under evaluation

Computer use closed-loop evaluation

An evaluation in which a model inspects an open application and uses its observed structure and feedback to recreate a functional version.

Also called Computer use closed loop.

source
1
model
1
lab adopt it
1
strongest
optional

How sources treat it

One count per evidence span, weakest treatment to strongest.

optional 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

Use Computer Use to inspect the currently open application, identify its page structure, core functionality, primary user flows, and interaction feedback, and recreate a functional version in the current directory.

optionalotherZ.ai

Filed alongside

Other methods under evaluation :: benchmark.