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

a ground-truth-based dynamic benchmark derived from off-the-shelf benchmark mixtures, which evaluates LLMs with a highly capable model ranking while running locally and quickly.

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.

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.

focuses on understanding how these models perform in various scenarios and analyzing results from an interpretability perspective.

a benchmark that evaluates large multimodal models (LMMs) on their ability to perform human-like mathematical reasoning.