Skip to main content

AndroidWorld

A mobile GUI agent benchmark for completing Android app workflows and on-device tasks.

How BenchLM shows AndroidWorld right now

BenchLM is tracking AndroidWorld in the local dataset, but exact-source verification records for these rows are still being attached. To avoid a blank benchmark page, BenchLM shows the current tracked rows below as a display-only reference table.

These tracked rows are useful for inspection and spot-checking, but until exact-source attachments are completed they should not be treated as fully verified public benchmark rows.

3 tracked modelsLocal tracked rowsAwaiting exact-source attachmentsDisplay only

Tracked score on AndroidWorld — April 16, 2026

BenchLM mirrors the published tracked score view for AndroidWorld. GLM-5V-Turbo leads the public snapshot at 75.7% , followed by Claude Opus 4.6 (62.0%) and Kimi K2.5 (43.1%). BenchLM does not use these results to rank models overall.

3 modelsAgenticCurrentDisplay onlyUpdated April 16, 2026

The published AndroidWorld snapshot is tightly clustered at the top: GLM-5V-Turbo sits at 75.7%, while the third row is only 32.6 points behind. The broader top-10 spread is 32.6 points, so the benchmark still separates strong models even when the leaders cluster.

3 models have been evaluated on AndroidWorld. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. AndroidWorld is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AndroidWorld

Year

2026

Tasks

Android app workflows

Format

Interactive mobile-agent evaluation

Difficulty

Complex mobile task completion

BenchLM tracks AndroidWorld as a display-only benchmark reference when providers publish exact values alongside broader GUI-agent summaries.

BenchLM freshness & provenance

Version

AndroidWorld 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Tracked score table (3 models)

1
GLM-5V-Turboglm-5v-turbo
75.7%
2
Claude Opus 4.6claude-opus-4-6
62.0%
3
Kimi K2.5kimi-k2-5
43.1%

FAQ

What does AndroidWorld measure?

A mobile GUI agent benchmark for completing Android app workflows and on-device tasks.

Which model leads the published AndroidWorld snapshot?

GLM-5V-Turbo currently leads the published AndroidWorld snapshot with a tracked score of 75.7%. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on AndroidWorld?

3 AI models are included in BenchLM's mirrored AndroidWorld snapshot, based on the public leaderboard captured on April 16, 2026.

Last updated: April 16, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.