Agentic language model systems can improve performance either by iterating on their own outputs or by using external tools in grounded environments. While these strategies can reduce error rates and substitute for larger models in some settings, their environmental cost remains relatively underexplored.

We present two complementary empirical studies that estimate the energy and carbon footprint of agentic AI across settings of increasing complexity. Study1 evaluates iterative verbal self-refinement: GPT-4.1-mini at $k = 1$--$5$ steps versus a GPT-4.1 single-pass baseline on two MATH benchmark splits. Study2 evaluates tool-augmented agentic coding: GPT-4.1-mini, Claude Opus4.6, and GPT-5.3-codex on SWE-bench Lite, where agents operate inside Docker-isolated environments with access to code execution and file editing tools. In Study1, $k=3$ refinements close a 16-percentage-point accuracy gap to within 1point, but nearly triple the carbon footprint relative to the cheap single-pass baseline while remaining below the GPT-4.1 single-pass baseline under the current token-based carbon scenario. In Study2, GPT-5.3-codex achieves the highest resolution rate in this sample (81.2%), ahead of Claude Opus4.6 (68.9%) and GPT-4.1-mini (25.0%), but resolved-task-normalized efficiency remains mixed: GPT-4.1-mini is lowest on estimated carbon and cost per resolved task, while GPT-5.3-codex delivers substantially higher task success. All carbon estimates cover output-token inference only; prompt tokens, which exceed 99% of tokens in Study2, and tool execution are not charged, so the figures are lower bounds on the full agentic footprint.