Skip to main content
BenchLM
Advertise

Benchmark profile

AndroidWorld

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

Data verified

Benchmark score on AndroidWorld — July 23, 2026

BenchLM mirrors the published score view for AndroidWorld. Qwen3.7 Plus leads the public snapshot at 81.0% , followed by Holo3.1-35B-A3B (79.3%) and Holo3.1-4B (71.0%). BenchLM does not use these results to rank models overall.

1Closed

Qwen3.7 Plus

Alibaba

qwen3-7-plus

81.0%
Overall 67.22Context 1M
2Open

Holo3.1-35B-A3B

H Company

holo3-1-35b-a3b

79.3%
Overall —Context 262K
3Open

Holo3.1-4B

H Company

holo3-1-4b

71.0%
Overall —Context 262K
5 modelsAgenticCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (5 models)

Score
1
Qwen3.7 PlusAlibaba · Closed
81.0%
2
Holo3.1-35B-A3BH Company · Open weight
79.3%
3
Holo3.1-4BH Company · Open weight
71.0%
4
Holo3.1-9BH Company · Open weight
71.0%
5
Qwen3.6-27BAlibaba · Open weight
70.3%

The published AndroidWorld snapshot places Qwen3.7 Plus first at 81.0%. The third row is 10.0 points behind. The broader top-10 range is 10.7 points, so the table still separates the published systems.

5 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.

GLM-5V-Turbo

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.

FAQ

What does AndroidWorld measure?

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

Which model scores highest on AndroidWorld?

Qwen3.7 Plus by Alibaba currently leads with a score of 81.0% on AndroidWorld.

How many models are evaluated on AndroidWorld?

5 AI models have been evaluated on AndroidWorld on BenchLM.

Compare Top Models on AndroidWorld

Qwen3.7 Plus vs Holo3.1-35B-A3BHolo3.1-35B-A3B vs Holo3.1-4BHolo3.1-4B vs Holo3.1-9BHolo3.1-9B vs Qwen3.6-27B
Last updated: July 23, 2026 · BenchLM version AndroidWorld 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.