AI SoftwareWeb linkPublished
HELM — Holistic Evaluation of Language Models
Stanford CRFM's living benchmark and leaderboards for transparent, holistic evaluation of language models.
About this resource
HELM evaluates language models across accuracy, calibration, robustness, fairness, bias, toxicity and efficiency, with public leaderboards and a reproducible framework. The original paper: arXiv:2211.09110. Source: https://crfm.stanford.edu/helm
benchmarksbenchmarkingevaluationLLM