Seoul: Samsung Electronics Co. has launched TrueBench, a platform designed to assess the productivity of artificial intelligence (AI) models within workplace environments. The announcement, made on Thursday, highlights Samsung's commitment to advancing AI capabilities in real-world applications.
According to Yonhap News Agency, TrueBench offers businesses a comprehensive set of metrics specifically aimed at tracking the productivity of large language models (LLMs) in various workplace settings. The platform addresses the growing demand for measuring AI productivity as companies increasingly adopt AI for various tasks.
Samsung noted that existing benchmarks predominantly focus on overall performance, are primarily English-centric, and are limited to single-turn question-answer structures. TrueBench aims to overcome these limitations by evaluating work-related tasks such as content generation and data analysis across 10 categories and 46 subcategories. The platform supports 12 languages, including Korean, English, and Japanese, making it more accessible to a global audience.
Cheun Kyung-whoon, Samsung's chief technology officer of the device experience division, emphasized the company's expertise and competitive edge in AI. He stated, "We expect TrueBench to establish evaluation standards for productivity and solidify Samsung's technological leadership."