LLM Stats (AndroidWorld): leaderboard

AndroidWorld as aggregated by LLM Stats — autonomous-agent tasks on a real Android emulator covering app interaction, navigation, and multi-step task completion.

Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around January 2027. 8 models tracked.

Top models

#ModelScoreOverall rank
1Qwen 3.8 Max85.3#35
2Qwen3.8-Flash-Next84.5#72
3Qwen 3.8 27B81.9#105
4Qwen 3.7 Plus81#92
5GLM-5V Turbo75.7#166
6Seed 1.870.7#139
7Qwen 3.6 27B70.3#170

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=llm-stats-androidworld · How It Works · Data refreshed daily, snapshot 2026-10-20.