OpenMobile‑2: Open‑Source Smartphone Agent Models Match Proprietary Competitors
Current overview (not historical)
Researchers have released OpenMobile‑2, two open‑source agent models built on Qwen3.5‑9B and Qwen3.6‑27B, along with the full training environment, data, and reproducibility guide. The models were retrained on 110 applications—including Taobao, JD.com, and Slack—to increase application diversity. On the AndroidWorld benchmark, they achieved 24.8 and 20.7 percentage‑point gains, respectively, while on the MobileWorld multi‑app task they improved by 14.5 percentage points, bringing them into direct competition with closed‑source models. The release demonstrates that open‑source agents can close the performance gap with proprietary systems, offering a transparent and reproducible alternative for mobile AI development.
Written with AI from the reporting · updated 10/25/2026
Expand the detailed fact route and sources
Story route
A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.
- 1Unclassified fact stationOct 25, 00:00recorded Oct 25, 15:51single sourcerevised
OpenMobile-2发布开源智能体模型
Read original source ↗ The DecoderReplay this moment in the explorerEvidence & revisions · 1 source records
- Subject：
- qwen
- Action：
- 发布两个智能体模型
- Object：
- 基于Qwen3.5的9B和Qwen3.6的27B参数模型
- Occurred (fact side)：
- Oct 25, 00:00
- Published (valid side)：
- Oct 25, 14:55
- First seen (known side)：
- Oct 25, 15:51
Fact stationSingle source · one-sided claimRevisedCopy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.
Uncertainty marks flag where to check the sources; they are not proven causation.
Report timeline
Explore every side through dated source reports.
- The DecoderRelated fact: single sourceSource report revisedOpenMobile‑2: Open‑Source Smartphone Agents Match Proprietary Models on 110‑App Benchmarks
Report first recorded Oct 25, 15:51
Researchers from Nanjing University, SenseTime, and other institutions released two open‑source smartphone agents built on Qwen3.5 (9 B parameters) and Qwen3.6 (27 B parameters). They provided the full training environment, data, and reproducibility instructions. The team rebuilt 35 popular Chinese apps (Taobao, JD, DiDi, Meituan) and added globally used services (Slack, Google Drive), creating a practice set of over 110 applications. Using simulated and real Android environments, they generated ~11,600 example workflows and >2,000 practice tasks, with automated success checks. The agents were trained with the help of Google’s Gemini 3.1 Pro as a teacher model. On the AndroidWorld benchmark, the 27 B model rose from 67.1 to 79.9 points and the 9 B model from 54.3 to 74.0 points, surpassing the predecessor OpenMobile‑1 (64.7). On the MobileWorld benchmark, the 27 B model improved from 35.9 to 50.4 points. On real Android devices, the 27 B model achieved 59.6 points on SPA‑Bench, the highest score among open models and close to Gemini 3.1 Pro.
Read original source ↗
Event discussion
Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.