Don't add chain-of-thought to reasoning models, give only the goal.

On o3/o4-mini-class models with built-in reasoning, explicit CoT prompting gained only ~2.9 to 3.1% accuracy while adding 20 to 80% latency and cost. Net loss. Reserve CoT for non-reasoning models (it lifts Gemini Flash 2.0 ~13.5%), and for reasoning models supply only the objective and constraints. Source: Wharton GenAI Labs