Saved in:
Bibliographic Details
Main Authors: Cao, Jinghan, Ma, Yu, Li, Xinjin, Ren, Qingyang, Chen, Xiangyun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.21389
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Large Language Models achieve remarkable performance but incur substantial computational costs unsuitable for resource-constrained deployments. This paper presents the first comprehensive task-specific efficiency analysis comparing 16 language models across five diverse NLP tasks. We introduce the Performance-Efficiency Ratio (PER), a novel metric integrating accuracy, throughput, memory, and latency through geometric mean normalization. Our systematic evaluation reveals that small models (0.5--3B parameters) achieve superior PER scores across all given tasks. These findings establish quantitative foundations for deploying small models in production environments prioritizing inference efficiency over marginal accuracy gains.