MobileGUI-VBench
Mobile-app task definitions covering everyday scenarios, with annotated preconditions and clarification requirements for evaluating agent behavior.
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
- Benchmarks
- Environment
- unspecified
- Topics
- evaluation, mobile-navigation, cross-app
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-17T02:42:32Z
- Resource ID
- url:d7a4f34a6a5202af5f64
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
Evaluation protocol
- Focus
- mobile task completion, clarification behavior, cross-app tasks
- Setting
- interactive
- Observations
- mobile app interfaces
- Actions / outputs
- mobile interface operations, clarification requests
- Evaluation
- Published task definitions include preconditions and clarification requirements; the metadata review does not independently validate the reported agent scores.
Scale and counting units
The card describes 140 single-app and 10 cross-app tasks. Task and app counts are different units.
Compare source-reviewed profiles
Recorded specifications
- disabled
- false
- download url
- https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/tree/main
- gated
- false
- hub id
- vivo-ai/MobileGUI-VBench
Explore related topics
Scope and limitations
Public task files are available as JSONL and XLSX with documentation. The card explicitly declares Apache-2.0 for the dataset, despite having no license field in its YAML metadata. It identifies mobile apps without fixing an operating-system taxonomy; model scores are not imported.
Related resources
- documented by: BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents
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 2026-10-17T02:42:32Z. Supports: name, kind, summary, environments, topics, scope, relations, details.
Content fingerprint
422ff6a557a1aabd8f6c6ef26e5fd05b992f4acf0e5128ab8bc437021fcc5ea7 - editorial primary review
Retrieved 2026-10-17T02:42:32Z. Supports: identity, release_status, details, licenses.data.
Content fingerprint
5850fc58f54c877cffe328dba2a0b5e3e98767637aae6d6efd9a037cf06eabce
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.