Agentic benchmark
AndroidWorld leaderboard
Every model the catalog carries a published AndroidWorld value for, ranked by that value.
CategoryAgentic
MeasureInteractive mobile-agent evaluation
TasksAndroid app workflows
DifficultyComplex mobile task completion
Published byGLM-5V-Turbo
A mobile GUI agent benchmark for completing Android app workflows and on-device tasks.
AndroidWorld ranking
9 models with a published AndroidWorld value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Interactive mobile-agent evaluation |
|---|---|---|---|
| 1 |  Qwen3.8-Omni-Flash | Alibaba | 87.1 |
| 2 | Qwen3.8 Max | Alibaba | 85.3 |
| 3 | Qwen3.8-Flash-Next | Alibaba | 84.5 |
| 4 | Qwen3.8-27B | Alibaba | 81.9 |
| 5 | Qwen3.7 Plus | Alibaba | 81.0 |
| 6 | HCHolo3.1-35B-A3B | H Company | 79.3 |
| 7 | HCHolo3.1-4B | H Company | 71.0 |
| 7 | HCHolo3.1-9B | H Company | 71.0 |
| 9 | Qwen3.6-27B | Alibaba | 70.3 |
Evidence key: Observed
Rows are ordered by the value GLM-5V-Turbo published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.