EleutherAI lm-evaluation-harness
Fields
engines/lm-eval-harnessNotes
Recorded because almost every quantization quality delta in this repo is an lm-eval number, and because the GGUF k-quant study pinned the exact harness version (v0.4.9.2) alongside its llama.cpp commit (b7600). That pairing matters: swapping harness versions has silently moved published GSM8K/MMLU/IFEval numbers before. ||| MAINTENANCE (dated fact, GitHub API, 2026-10-04): last commit 2026-09-14 (0.7 months before this record), latest release v0.4.13 published 2026-08-31, 460 contributors (distinct committers including anonymous), open_issues_count 1115 (issues PLUS pull requests - see [[ev-github-open-issues-count-includes-pull-requests]]), not archived, 14129 stars. See [[ev-maintenance-status-is-four-dated-facts]] for how to read this fact set.
Cross-references
This record references no other records — it is a leaf. It is cited by 2.