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.
See official site
evaluates LLM's ability to call external functions/tools.
See official site
A pioneering benchmark specifically designed to assess honesty in LLMs comprehensively.
See official site
An Automatic Evaluator for Instruction-following Language Models using Nous benchmark suite.
See official site
Exploring the Intelligence of Large-scale MoE Model.
See official site