Google just changed how it grades the AI models you use for Android coding

Google resets its Android Bench leaderboard with a new testing framework and eight new models.The Latest Tech News, Delivered ...
Android

Google Changes the Rules for Ranking Android Coding AI—and Gemini Is Still Lagging Behind

Google upgraded its Android Bench coding developer leaderboard by adopting the Harbor sandbox framework and adding eight new AI models to the testing ecosystem. Anthropic’s Claude Fable 5 secured ...
The Next Web

AI’s hacking skills are outgrowing the tests built to measure them

Frontier AI models are outrunning the benchmarks built to measure their hacking skills, just as a 1 August US deadline for new testing standards looms.
XDA Developers on MSN

I asked Claude Code, Codex, and Google Antigravity to build the same complex website – only one felt like a seasoned developer

Code was easy, polish was not.