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

ModelOrganizationReported valueReportedEvidence
Qwen3.8 MaxQwen0.7512026-08-02evidence

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.