Published May 27, 2024 | Version v1

Data of LLMs evaluation

Description

This data is the outcome of evaluating the performance of three LLMs, including gpt-4o, gemini-1.5-pro, and claude-sonnet, on five tasks related to our system's functionalities, including generating corresponding pronunciation, example, synonyms, antonyms and contextual explanation.

Files

Files (25.7 kB)

Name Size Download all
md5:130648882ea3de61be25bb2131198435
25.7 kB Download