Benchmarks

ScreenSpot

GUI grounding test set of 1,272 screenshot instructions from iOS, Android, macOS, Windows and web interfaces, each labeled with the target element's bounding box.

AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.

Original source ↗Read as MarkdownRecord JSON

What is this resource?

Resource type
Benchmarks
Environment
cross-platform
Topics
grounding, evaluation
Record publication date
Not recorded
Evidence retrieved
2026-10-16T06:38:26Z
Resource ID
url:7abb418096432f56c685

What licenses are recorded?

Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.

Code
Not recorded
Data
apache-2.0 (publisher model/dataset card)
Document
Not recorded
Weights
Not recorded

Evaluation protocol

Focus
single-step GUI element grounding
Setting
offline
Observations
screenshot, English instruction
Actions / outputs
predicted click point; a predicted box is reduced to its center
Evaluation
The SeeClick evaluator scores whether the predicted point falls inside the target box, with platform and text/icon breakdowns. The Hub packaging uses xyxy boxes, whereas the original evaluator reads xywh and converts it; adapt the loader to the chosen release.

Scale and counting units

Offline, zero-shot evaluation across mobile, desktop, and web. The card explicitly excludes training use in its intended-use description. Public API reports ungated Parquet files and canonical Hub id bevaya/ScreenSpot; the catalog identity is preserved. Apache-2.0 is the Hub data declaration. No runtime or underlying screenshot rights audit was performed.

Compare source-reviewed profiles

Recorded specifications

disabled
false
download url
https://huggingface.co/datasets/rootsautomation/ScreenSpot/tree/main
gated
false
hub id
bevaya/ScreenSpot
languages
["en"]
modalities
["image", "text"]

Explore related topics

GUI groundingEvaluation

Primary evidence and verification

Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.

  1. editorial primary review

    Retrieved 2026-10-16T06:38:26Z. Supports: name, kind, summary, environments, topics, scope, relations, details.benchmark_protocol.

    Content fingerprint9e2d2a2c076032225911ae1032b548eafa6331ea81a2779632610f0f1c82dfd9
  2. editorial primary review

    Retrieved 2026-10-17T14:10:00Z. Supports: details.benchmark_protocol.

    Content fingerprint5ab2240c064502f75a6726311e10e7724ab7055347697f883b15a6ee8e7d00a6
  3. editorial primary review

    Retrieved 2026-10-17T14:22:04Z. Supports: details.benchmark_protocol.

    Content fingerprinteb72113eefd4868114f8a8105eba2d3385da9034a5b3a4860661e03ae7dcae15
  4. huggingface api

    Retrieved 2026-10-16T06:38:26Z. Supports: details, licenses.data.

    Content fingerprint9e2d2a2c076032225911ae1032b548eafa6331ea81a2779632610f0f1c82dfd9
  5. huggingface repository identity

    Retrieved 2026-10-17T19:14:56Z. Supports: aliases.

    Content fingerprintaf0c4babeff84158ff196b54bf47242923bbf502d2805a1dd4eb52dba44be89c
  6. huggingface repository identity

    Retrieved 2026-10-17T19:14:56Z. Supports: aliases.

    Content fingerprintaf0c4babeff84158ff196b54bf47242923bbf502d2805a1dd4eb52dba44be89c

Suggest a correction

Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.