Google let an agent optimise a 205,000-line repo overnight. Two of six changes shipped, and the holdout benchmark is why

Mon, 26 Oct 2026 11:10:00 +0000

Google’s Agent Development Kit (ADK) team pointed Gemini 4 Argon at the google/adk-python repository, about 205,000 lines across nearly 800 source files, and left it running for 11 hours. It proposed six optimisations across 32 files. Maintainers shipped two and rejected four, according to Google’s write-up .

Gemini 4 Argon costs half as much per token as Opus 5.5. Per task, it doesn't

Wed, 21 Oct 2026 11:08:00 +0000

Google’s Gemini 4 Argon is listed at $2 per million input tokens and $10 per million output, exactly half of Claude Opus 5.5’s $4 and $20. Artificial Analysis then ran both at high effort and found Argon costs more per task: $1.99 against $1.82. The cheaper model spends more tokens to get there.

Gemini on Tokenise

Google let an agent optimise a 205,000-line repo overnight. Two of six changes shipped, and the holdout benchmark is why

Gemini 4 Argon costs half as much per token as Opus 5.5. Per task, it doesn't