benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Round-trip time dominates remote browser performance because one page load can mean thousands of CDP round trips, so placing the browser near the AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → often beats micro-optimizing Chromium. Measuring connect separately exposes work deferred out of the create call.
