Google overhauled how it ranks AI models for Android coding, updating its Android Bench, launched in March, to run on a new testing system called Harbor. The change reshaped the standings, with Claude Fable 5 taking the top spot. Android Bench measures how well AI models handle real Android development tasks, including updating old code to Jetpack Compose, handling wearable device networking, and fixing project-specific bugs. The core change is the switch to the Harbor framework, which runs tests inside secure sandbox environments, replacing the previously used mini-swe-agent. Because the testing method changed, Google re-ran and rescored every model to set a fresh baseline. Google also added eight new models to the leaderboard, including Claude Fable 5, Claude Sonnet 5, Claude Opus 4.8, GLM 5.2, Kimi K2.7 Code, MiniMax M3, Qwen 3.7 Plus, and Qwen 3.7 Max. Claude Fable 5 now leads with a score of 84.5%, followed by GPT-5.5 at 80.2% and Claude Sonnet 5 at 76.2%. Among open-weight models, GLM 5.2 leads at 72.2%, followed by Kimi K2.7 Code at 70.4%. The results proved awkward for Google as its own Gemini models continued to lag on their home turf. Top performance also carries a