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

a large-scale Document Visual Question Answering (VQA) dataset designed for complex document understanding, particularly in financial reports.

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

a multimodal question-answering benchmark designed to evaluate AI models' cognitive ability to understand human beliefs and goals.

an expert-driven benchmark for Chineses LLMs.

evaluates LLM's ability to call external functions/tools.