a benchmark that evaluates large language models on a variety of multimodal reasoning tasks, including language, natural and social sciences, physical and social commonsense, temporal reasoning, algebra, and geometry.

A pioneering benchmark specifically designed to assess honesty in LLMs comprehensively.

CompassRank is dedicated to exploring the most advanced language and visual models, offering a comprehensive, objective, and neutral evaluation reference for the industry and research.

an expert-driven benchmark for Chineses LLMs.

a benchmark platform designed for evaluating large language models (LLMs) on a range of tasks, particularly focusing on their performance in different aspects such as natural language understanding, reasoning, and generalization.

a benchmark designed to assess the performance of multimodal web agents on realistic visually grounded tasks.