Analysis of LLM Performance on AWS Bedrock: Receipt-item Categorisation Case Study
This study addresses cost-effective model selection for receipt categorization in production systems, but it is incremental as it applies existing methods to new data.
This paper tackled the problem of evaluating large language models for receipt-item categorization by comparing four models on AWS Bedrock, finding that Claude 3.7 Sonnet achieved the best balance between accuracy and cost efficiency.
This paper presents a systematic, cost-aware evaluation of large language models (LLMs) for receipt-item categorisation within a production-oriented classification framework. We compare four instruction-tuned models available through AWS Bedrock: Claude 3.7 Sonnet, Claude 4 Sonnet, Mixtral 8x7B Instruct, and Mistral 7B Instruct. The aim of the study was (1) to assess performance across accuracy, response stability, and token-level cost, and (2) to investigate what prompting methods, zero-shot or few-shot, are especially appropriate both in terms of accuracy and in terms of incurred costs. Results of our experiments demonstrated that Claude 3.7 Sonnet achieves the most favourable balance between classification accuracy and cost efficiency.