Revision History
HELM (Holistic Evaluation of Language Models) · 6 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected HELM's 2022 findings on instruction tuning and open versus closed models, the HELM MMLU description of vendor-reported score gaps, the false claim that AIR-Bench was absorbed into HELM Safety, a miscited 'cheating models' claim, MedHELM's 2026 publication date, HELM's maintenance-mode status (leaderboards no longer receive new evaluations), and the Open LLM Leaderboard v2's 2025 retirement (plus 21 minor fixes)
Version 6 · Nov 5, 2026, 07:11 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:06 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:44 PM
- Initial AI-authored creation (4100 words).
Version 2 · May 21, 2026, 08:22 AM