Benchmark
AndroidWorld
AndroidWorld evaluates an agent's ability to operate in real Android GUI environments, completing multi-step tasks by perceiving screen content and…
- Modality
- multimodal
- Categories
- agents, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 5
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GLM-5V-Turbo | Z.ai | 0.757 | 2026-04-02 | evidence |
| Qwen3.6-27B | Qwen | 0.703 | 2026-04-21 | evidence |
| Qwen3.7-Plus | Qwen | 0.81 | 2026-05-31 | evidence |
| Qwen3.8 Max | Qwen | 0.853 | 2026-08-02 | evidence |
| Qwen3.8-27B | Qwen | 0.819 | 2026-08-14 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.