AndroidBench
Progress Over Time
Interactive timeline showing model performance evolution on AndroidBench
State-of-the-art frontier
Open
Proprietary
AndroidBench Leaderboard
1 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 2.4T | 1.0M | $1.65 / $4.95 |
Notice missing or incorrect data?
What is AndroidBench?
AndroidBench evaluates coding agents on Android application development tasks.
AndroidBench is a multimodal benchmark evaluating models on agents, code, and tool calling tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.8, with the leader at 0.8.
Compare leaders on the best AI for agents, best AI for code and best AI for tool calling leaderboards.
Current leaders
Qwen3.8 Max from Alibaba Cloud / Qwen Team currently leads the AndroidBench leaderboard with a score of 0.751 across 1 evaluated AI models.
FAQ
Common questions about the AndroidBench benchmark and leaderboard.