llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeBenchmarksmultimodalAndroid Control High_EM

multimodal benchmark

Android Control High_EM

Android device control benchmark using high exact match evaluation metric for assessing agent performance on mobile interface tasks

Updated Aug 11, 2026

Models3
Model coverage3
MetricScore
EvidenceB

On this page

  • Ranking
  • Distribution
  • Highlights
  • About
  • FAQ

Android Control High_EM Ranking

Higher score ranks better on this benchmark.

3 rows
Columns

Show columns

1ACQwen2.5 VL 32B InstructAlibaba Cloud / Qwen Team69.6%100.0%3CAug 11, 2026
2ACQwen2.5 VL 72B InstructAlibaba Cloud / Qwen Team67.4%50.0%3CAug 11, 2026
3ACQwen2.5 VL 7B InstructAlibaba Cloud / Qwen Team60.1%0.0%3CAug 11, 2026

Android Control High_EM Score Distribution

A closer view of the leading scores on this benchmark.

Android Control High_EM

Android Control High_EM Highlights

The leading models and scores on this benchmark.

Rank #1Qwen2.5 VL 32B Instruct69.6%Rank #2Qwen2.5 VL 72B Instruct67.4%Rank #3Qwen2.5 VL 7B Instruct60.1%

What is Android Control High_EM?

What Android Control High_EM measures and how its scores work.

Android device control benchmark using high exact match evaluation metric for assessing agent performance on mobile interface tasks

Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.

Family
Android Control High_EM
Modality
multimodal
Primary category
multimodal
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
android-control-high-em|llm-stats-current

Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about Android Control High_EM.

Which model scores highest on Android Control High_EM?

Qwen2.5 VL 32B Instruct is currently ranked first with 69.6%.

What does Android Control High_EM measure?

Android device control benchmark using high exact match evaluation metric for assessing agent performance on mobile interface tasks

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

3 model results are currently shown.

Does this benchmark affect the overall score?

Yes. This benchmark can contribute to the current LLMBoard capability score.

Rankings

OverallCodingText ArenaPricing

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai