Multi-modal large model evaluation method and device, equipment, storage medium and product

Abstract

The invention provides a multi-modal large model evaluation method and device, equipment, a storage medium and a product, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a test plan for a multi-modal large model; generating a test data set based on the test plan, and randomly splitting the test data set into test question data and answer data corresponding to the test question data; inputting the test question data into the multi-modal large model to obtain an answer result output by the multi-modal large model; and comparing the answer result with the answer data to obtain an evaluation result for the multi-modal large model. By adopting the method and the device, the accuracy of the evaluation result obtained by evaluating the multi-modal large model can be ensured, so that the evaluation result is more stable and reliable.

Images