Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #16312

Android Bench 2.0

Related event timeline, sources and context from the news index.

EVENT TIMELINE

2

CODING · 1 SOURCE · The Decoder

Google opens Android Studio Rabbit 2 to third‑party AI agents and adds Gemini‑powered APIs

At the Android Dev Summit Google announced Android Studio Rabbit 2 will support a 'Bring Your Own Agent' workflow via an open Agent Client Protocol, letting developers run over 40 external coding agents (including Anthropic and OpenAI) inside the IDE and CLI. The company also introduced new tools and APIs — an alpha Agentic API powered by Gemini Nano 4 for local on‑device agents, a beta AppFunctions API, Agent‑to‑UI (A2UI) for Jetpack Compose, and a Connected Apps Platform preview — plus hardware tie‑ins such as the XREAL AURA Android XR smart glasses.

8.0

MODELS · 1 SOURCE · InfoQ AI, ML & Data Engineering

Google releases Android Bench 2.0 with long‑horizon tasks, agentic evaluation, and continuous scoring

Google published Android Bench 2.0, a major update to its benchmark for evaluating AI models on Android development tasks that adds long‑horizon tasks (LHTs), agentic evaluation (using providers' agents), and a continuous, multi‑factor scoring system instead of binary pass/fail. The new dashboard lists recent models (e.g., Gemini 3.8/3.7, OpenAI GPT‑6, Anthropic Fable 5.1, Kimi K3, Qwen 3.8 Max); at the time of reporting Claude Opus 5.5 led LHT pass rates at 32%, with GPT 6 Astra at 28%.

7.0