ScreenSpot-Pro

Reported in recent model launches

These model reports include this benchmark. Their harnesses, task subsets, scoring policies, and resource budgets can differ; follow each report’s evaluation notes before joining the numbers.

What it measures

A model must locate the interface element referred to by a user instruction on a professional screenshot.

How to read the result

This isolates the grounding step in computer use. Check whether the selected location corresponds to the intended control, not merely a visually similar label.

Limits and comparison traps

Successful pointing does not establish that a whole workflow can be completed. Pin screenshot resolution and whether tools or crops were available.

Benchmark reference notes

High-resolution professional software GUI grounding benchmark (CAD, IDEs, Adobe/Blender, scientific software).

Where this fits in an evaluation suite

A transcript that says “done” is weaker evidence than the verified final state. Track policy violations, recoveries, and invalid attempts alongside success.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

Pin the benchmark release, task split, model configuration, tools, sampling budget, and evaluation harness described by the primary source.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.