multimodal benchmark
MobileWorld Leaderboard
MobileWorld is a multimodal benchmark for evaluating agents on real mobile-device tasks.
Updated Sep 5, 2026
Models3
Model coverage3
MetricScore
EvidenceB
MobileWorld Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score77.80% | Percentile100.00% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelBY | Score73.10% | Percentile50.00% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelBY | Score70.00% | Percentile0.00% | Participants3 | EvidenceC | Evaluated |
MobileWorld Highlights
The leading models and scores on this benchmark.
MobileWorld Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MobileWorld
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MobileWorld?
What MobileWorld measures and how its scores work.
MobileWorld is a benchmark for evaluating multimodal agents in mobile environments.
It measures GUI grounding, navigation, and multi-step task completion on real mobile-device tasks.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MobileWorld
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MobileWorld.
Which model scores highest on MobileWorld?
Qwen3.8 Max is currently ranked first with 77.80%.
What are the top three models on MobileWorld?
The current leaders are Qwen3.8 Max (77.80%), Seed 2.1 Pro (73.10%), and Seed 2.1 Turbo (70.00%).
Which MobileWorld model has the lowest official input price?
Qwen3.8 Max has the lowest matched official input price at $2.0 input / $6.0 output per 1M tokens.
Which models are fastest among MobileWorld results?
The fastest matched records are Qwen3.8 Max (60.87 tok/s via DeepInfra).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.