Sittiphol Phanvilai

CostOpt: Quantifying Cost-Accuracy Tradeoffs in LLM Prompting Strategies: An API-Only Cross-Provider Factorial Study on CostBench 500

2026 · Zenodo (CERN European Organization for Nuclear Research)

Current LLM reasoning strategy evaluations emphasize accuracy while ignoring cost, despite cost varying by 10$\times$ or more across configurations. We present \textsc{CostOpt}, a framework for cost-aware strategy evaluation, and \textsc{CostBench 500}, a curated benchmark of …