ScreenQA
About 86,000 human-written question-answer pairs over 35,000 Rico mobile screenshots, plus ScreenQA Short and ComplexQA variants, for benchmarking screen content understanding.
AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.
What is this resource?
- Resource type
- Datasets
- Environment
- android
- Topics
- screen-understanding
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-16T06:36:01Z
- Resource ID
- github:google-research-datasets/screen_qa
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
- Not recorded
- Document
- Not recorded
- Weights
- Not recorded
Dataset profile
- Supervision
- screen question answering, answer grounding
- Modalities
- questions, answers, screen references, bounding boxes
- Formats
- JSON
- Splits
- train, validation, test
Scale and counting units
- 68,951 question-answer pairs — original ScreenQA train split source
- 8,614 question-answer pairs — original ScreenQA validation split source
- 8,419 question-answer pairs — original ScreenQA test split source
All questions for a given screenshot share one split. ScreenQA Short reuses the same questions/screens; ComplexQA is a separate extension. Do not add these variants as independent original examples.
Compare source-reviewed profiles
Explore related topics
Related resources
Primary evidence and verification
Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.
- editorial primary review
Retrieved 2026-10-16T06:36:01Z. Supports: name, kind, summary, environments, topics, scope, relations, details.dataset_profile.
Content fingerprint
7d1bfe7d6eddd5d3fc4c33d4814de3cabf7a6b6fd3d3f85ba4c2b33036bf8867
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.