Holistic Evaluation of Language Models

Our summary

A benchmark that scores language models on a taxonomy of scenarios against seven metrics — accuracy, calibration, robustness, fairness, bias, toxicity, efficiency — to make model quality transparent and comparable.

Why it matters

The exemplar of benchmark evaluation as a standing, comparable measurement rather than a one-off score — the longitudinal lens for tracking models across versions.

Cited by these methods

Cite this