multimodal benchmark
Android Control High_EM Leaderboard
Android device control benchmark using high exact match evaluation metric for assessing agent performance on mobile interface tasks
Updated Aug 17, 2026
Models3
Model coverage3
MetricScore
EvidenceB
Android Control High_EM Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score69.6% | Percentile100.0% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score67.4% | Percentile50.0% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score60.1% | Percentile0.0% | Participants3 | EvidenceC | Evaluated |
Android Control High_EM Highlights
The leading models and scores on this benchmark.
Android Control High_EM Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Android Control High_EM
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis android control high_em AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACQwen2.5 VL 32B InstructAlibaba Cloud / Qwen Team
- Score
- 69.6%
Strengths
- Ranks #1 of 3 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures Android Control High_EM, not total model capability
- 02ACQwen2.5 VL 72B InstructAlibaba Cloud / Qwen Team
- Score
- 67.4%
Strengths
- Ranks #2 of 3 compared models
- 50th percentile on this benchmark
- C evidence result
Considerations
- This result measures Android Control High_EM, not total model capability
- 03ACQwen2.5 VL 7B InstructAlibaba Cloud / Qwen Team
- Score
- 60.1%
- Price
- $0.35 input / $1.1 output per 1M tokens
Strengths
- Ranks #3 of 3 compared models
- 0th percentile on this benchmark
- C evidence result
Considerations
- This result measures Android Control High_EM, not total model capability
Selection summary
Best AI Models for Android Control High_EM
Qwen2.5 VL 32B Instruct currently leads Android Control High_EM with 69.6%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
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.