Revision History
RULER (benchmark) · 8 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 the headline finding (the 17-model paper reports half, not four, of the models passing at 32K), the top model (Gemini-1.5-Pro, not GPT-4, in the published version), the ChatGLM row, the Jamba-base result, and the claim that Gemini 1.5 Pro and Llama 3.1 were not evaluated; replaced a limitation quote that is not in the paper with the paper's actual wording; updated a stale leaderboard claim (plus 23 minor fixes)
Version 8 · Nov 5, 2026, 08:54 AM
- Improve internal links (2026-10-13)
Version 7 · Oct 13, 2026, 10:15 AM
- Added 6 contextual internal links
Version 6 · Jul 23, 2026, 03:27 PM