Qwen launches three mobile agents, open-sources benchmarks with 90% end-to-end success
CurieuxExplorer · x · 2026-09-25
Alibaba's Qwen officially introduced Qwen Intelligence, bringing personal AI to phones, launching with three SOTA agents:
- Mobile Planner Agent: plans, decomposes, and orchestrates complex tasks; #1 on MobilePA-Bench, its Business & Memory variants
- Mobile-Use Agent: API-first with GUI fallback; MobileWorld 82.1, MobileWorld-Real 92.2, AndroidDaily 97.2, 90% end-to-end success rate
- Mobile Creative Agent: one sentence to ready-to-use assets; image generation in 3s, about 2x faster than leading peers
Qwen also open-sourced its benchmark suite — MobilePA-Bench, MobileWorld, MobileWorld-Real, and MobileWorld-Safety — covering planning, cross-app execution, and safety.
Related event: Qwen Unveils Mobile Agent Suite and Open Benchmark(2 posts)→
More from coding & agent
- Running 6 concurrent ds41-flash agents: persistent enough to need pi-durable coordination — dbreunig · 2026-11-11
- OpenAI roundup: architecture details of four GPT-Live voice agent builds — pbbakkum · 2026-11-11
- Ex-Apple keyboard engineer Ken Kocienda open-sources Tug, a macOS AI coding app in beta — Scobleizer · 2026-11-11
- Carbon tops Abundant Labs agent benchmark with 14/20 vs Opus 5.5 and GPT-6 — amankhan · 2026-11-11
- VS Code Copilot falls back from Computer Use and Python to PowerShell + COM to build an Excel workbook — dfinke · 2026-11-11
- LangChain's proactive agent engineering: agents will assign tasks to you — LangChain · 2026-11-11