Benchmark definition

AndroidWorld

2024

ActiveANDROIDWORLD_2024

Applicability does not mean evaluated; benchmark result/model score data is outside this UI contract.

Compare with others

About

Description: AndroidWorld
What it measures: AndroidWorld
Comparison guidance: Not published
Intended difficulty: Not published

Not recorded for this benchmark: what it does not measure, why it matters, motivation, gap addressed.

Classification

Categories: Mobile AgentComputer UseAgenticMultimodal
Domains: None recorded
Evaluation style: None recorded

Structure

2 scenarios. Applicability can differ between them.

Scenarios

Screenshot / visually grounded configurationObservation profile
Accessibility/UI-tree text configurationObservation profile

Tasks

Computer UseMobile Gui Interaction

Metrics

What a result on this benchmark would be reported as. ctxdex does not carry results.

Metric	Role	Direction	Unit
Task Success Rate Canonical Batch-2 metric code TASK_SUCCESS_RATE; benchmark-specific formula/parameters remain on benchmark_metric and methodology records.	Primary	Higher is better	Percent
Partial Completion Score Benchmark-defined normalized partial progress/checkpoint score. Exact source formula MUST be preserved in metric parameters/methodology.	Secondary	Higher is better	Score

Methodology

Task generationThis definition

Task templates instantiate concrete episodes from parameters/seeds; reproducible runs must retain seed/parameter provenance.

Source lane: L4

Evaluation environment

What the benchmark's harness provides and allows. These are properties of the environment, not model requirements, and applicability does not test for them.

Mobile GUI · Mobile emulator

Actions: Coordinate pointer actionKeyboard inputProgrammatic environment action
Observations: ScreenshotAccessibility treeStructured environment state
Session: Turn based actions
Reset: Task initialize teardown
Network: External allowed
State persists per: Episode
Grounding: Mixed

Evaluation style: Not recorded
Environment summary: Not published

Model requirements

Required conditions decide applicability. Relevant ones describe what the benchmark exercises and decide nothing.

Required · decides applicability

Whole benchmark

Text (input)

Relevant · informational

Image (input)Complex reasoningGeneral purpose models

CTXDEX models

51 of the 58 active, preview, experimental models meet this benchmark’s recorded requirements, at some scope. Applicable means the requirements are met, not that the model was evaluated.

View all 51 applicable models →

Applicable · full: 51
Applicable · components: 0
Applicable · scenarios: 0
Conditionally applicable: 0
Not recorded: 7

Counted over 58 models in the default lifecycle scope (active, preview, experimental).

Every required condition, for the whole benchmark, is recorded as supported. Each line is one recorded condition and why it counts.

Ctxdex Efficient 3
Ctxdex Efficient
Full benchmark
Every one of the 1 required conditions is recorded as supported.
- MODALITY:INPUT:TEXTthe catalogue records SUPPORTED for TEXT (input)
Ctxdex Enterprise 4
Ctxdex Enterprise
Full benchmark
Every one of the 1 required conditions is recorded as supported.
- MODALITY:INPUT:TEXTthe catalogue records SUPPORTED for TEXT (input)

Preview holds 12 of 51. View all →

Applicability/relevance ordering only; never a performance ranking.

Scale

20
Application
Total · Exact
PARAMETERIZED/SEED_DEPENDENT
Concrete episode count
Total · Exact
116
Task
Total · Exact

Data and access

UnknownDataset, evaluation code, leaderboard, peer review and maintenance status are all unrecorded for this benchmark.

Coverage

Languages, regions: None recorded
Coverage summary: Not published

Limitations

None recorded

Lineage

Family: FamilyAndroidWorld
Related: None recorded
Changes: None recorded

Sources

https://github.com/google-research/android_world ↗Official repository · Benchmark official
https://arxiv.org/abs/2405.14573 ↗Research paper · Original creator
https://google-research.github.io/android_world/ ↗Official website · Benchmark official

Freshness

Content version: B2-1.0
Last reviewed: 2026-09-23
Refresh model: Unknown
Time sensitivity: Unknown
Benchmark data: c40cccac878af5d0

13 contract fields are empty for every benchmark in this release and are not shown: applicability groups, conditional requirements, feature requirements, model relevance domains, required capabilities, openness summary, reference artifacts, interaction protocols, tool protocols, benchmark last major refresh at, short name, target expertise level, target population.