Benchmark
AndroidBench
AndroidBench evaluates coding agents on Android application development tasks.
- Modality
- multimodal
- Categories
- agents, code, tool_calling
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 1
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3.8 Max | Qwen | 0.751 | 2026-08-02 | 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.