eval-harness

metric

n_pairs

better
neutral: a description
kind
descriptive: says what the output was, never whether it was good
decides
no goal
weighed by
no goal
recorded on
summeval_100

01what it measures, and how

Pairwise mode: how many of the article's sampled pairs the experts ranked apart, the pairs pair_agreement is averaged over.

A project explains its own metric at length with METRIC_DESCRIPTIONS = {"n_pairs": {"summary": "…", "details": "…"}}.

02on summeval_100

gold/summeval_100se_gemma_l_n100_pairwise_v1: 7.49se_qwen_s_n100_pairwise_v1: 7.49se_random_n100_pairwise_v1: 7.496.99better · 7.99

scored against silverscored by a judgewrote the reference it is scored againstscored against a label set, not a reference setunmarked rows are scored against gold