a meta-benchmark that evaluates how well factuality evaluators assess the outputs of large language models (LLMs).

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

a benchmark for evaluating AI models across multiple academic disciplines like math, physics, chemistry, biology, and more.

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.

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