Drop explicit chain-of-thought for reasoning models — it's redundant and adds cost

K2view·medium signal

Chain-of-thought still gives standard models a large lift (~19 points on MMLU-Pro), but reasoning models (o-series, Claude Extended Thinking, Gemini Thinking) already reason internally, so adding 'think step by step' just inflates latency and token spend with no accuracy gain. Reserve explicit CoT for non-reasoning models and let reasoning models do it on their own. Mismatching the two is a common, silent cost leak in agentic loops.