Google resets Android Bench leaderboard with new testing framework, adds eight new models

Google updates its Android Bench leaderboard with a new testing framework and eight new AI models for Android coding. The reset aims to improve grading accuracy, but Gemini models still trail behind competitors.

• Google just changed how it grades the AI models you use for Android coding
• Google updates Android Bench with new LLMs, but Gemini still lags behind
• Google is changing how it judges AI models for Android coding, updates list with Fable 5