ScreenSpot.

The ScreenSpot-Pro dataset is designed for GUI grounding evaluation. It consists of 1,581 instruction-image pairs across 23 applications, with each sample including a high-resolution screenshot and a natural language instruction describing the target UI element. The dataset is categorized into 6 application types: Development and Programming, Creative Software, CAD and Engineering, Scientific and Analytical, Office Software, and Operating System Commons.

Best published scores.

No results indexed yet — be the first to submit a score.

Neighbouring benchmarks.

Other Few-Shot Image Classification datasets on Codesota.

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

• 01A public checkpoint or API endpoint
• 02A reproduction script with frozen commit + seed
• 03Declared evaluation environment (Python, deps)
• 04One row per metric declared by this dataset
• 05A contact so we can follow up on discrepancies