Android Bench 2.0 puts coding agents at 28%

Google’s Android Bench 2.0 puts OpenAI’s GPT-6 Astra at a 28% pass rate on long-horizon Android tasks, versus roughly 91% on the benchmark’s original incremental tasks. Google’s benchmark release says these tasks span work taking engineers multiple days or a week and score functionality, visual fidelity, regressions, and structural constraints. Builders should file the gap beside OctoBench’s harness comparison: model leaderboards still understate how much task length and harness decide whether coding agents finish.