multimodal benchmark
MobileMiniWob++_SR
MobileMiniWob++ SR (Success Rate) is an adaptation of the MiniWob++ web interaction benchmark for mobile Android environments within AndroidWorld. It comprises 92 web interaction tasks adapted for touch-based mobile interfaces, evaluating agents' ability to navigate and interact with web applications on mobile devices.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
MobileMiniWob++_SR leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 91.4% | 100.0% | 2 | C | |
| 2 | AC | 68.0% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
MobileMiniWob++_SR highlights
The top published results on this benchmark's own scale.
What is MobileMiniWob++_SR?
Definition and scoring fields from the benchmark registry.
MobileMiniWob++ SR (Success Rate) is an adaptation of the MiniWob++ web interaction benchmark for mobile Android environments within AndroidWorld. It comprises 92 web interaction tasks adapted for touch-based mobile interfaces, evaluating agents' ability to navigate and interact with web applications on mobile devices.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MobileMiniWob++_SR
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mobileminiwob++-sr|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MobileMiniWob++_SR.
Which model scores highest on MobileMiniWob++_SR?
Qwen2.5 VL 7B Instruct is currently ranked first with 91.4%.
What does MobileMiniWob++_SR measure?
MobileMiniWob++ SR (Success Rate) is an adaptation of the MiniWob++ web interaction benchmark for mobile Android environments within AndroidWorld. It comprises 92 web interaction tasks adapted for touch-based mobile interfaces, evaluating agents' ability to navigate and interact with web applications on mobile devices.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.