Blog / Benchmarks
2 articles

Benchmarks

All posts tagged with #Benchmarks

METR measured the AI-improving-AI loop inside Anthropic. The number is 2x.

METR measured the AI-improving-AI loop inside Anthropic. The number is 2x.

An outside evaluation of 11 weeks of Anthropic's internal R&D data finds capabilities improving at twice the previous rate, driven mostly by AI doing AI research — with most of the evidence redacted.

Read Article
Your AI router probably isn't routing

Your AI router probably isn't routing

AutoBench audited seven LLM routers across seventeen configurations and none beat just calling one mid-priced model every time. Here is what that means for your inference bill, and what to do about it.

Read Article