List your company

Foundation Model Selection on 100 diverse natural language user queries (test)

75.76Average Top-1REMSA
67.034469.299771.56573.8303Nov 21, 2025

Evaluation results

MethodLinks
REMSALLM Backbone=GPT-4.12025.1175.7675.0321.33400.34
REMSA-NaiveLLM Backbone=GPT-4.12025.1172.67722037.330.29
UNSTR.-RAGLLM Backbone=GPT-4.12025.1171.2368.3913.3330.670.24
DB-RetrievalLLM Backbone=GPT-4.12025.1167.3768.871217.330.23