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.

an expert-driven benchmark for Chineses LLMs.

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

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

a biomedical question-answering benchmark designed for answering research-related questions using PubMed abstracts.

benchmark designed to evaluate large language models (LLMs) on solving complex, college-level scientific problems from domains like chemistry, physics, and mathematics.