Revision History
Llama 3.2 · 10 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 Llama 3.1 8B IFEval (80.4, not 76.5) and Hellaswag (78.7, not 82.0) scores and the 3B-vs-8B IFEval claim built on them; corrected the timing of the quantized 1B/3B release (October 24, 2024, not at launch); removed an unsupported claim that GPT-4o-mini led the 90B model on MMMU; and corrected the EU restriction rationale, which Meta and Axios tied to GDPR, not the EU AI Act (plus 21 minor fixes)
Version 10 · Nov 2, 2026, 01:22 PM
- Improve internal links (2026-10-13)
Version 8 · Oct 13, 2026, 10:21 AM
- Added 6 contextual internal links
Version 7 · Jul 23, 2026, 03:29 PM
- Pre-update snapshot before enhancement to 4573 words.
Version 2 · May 17, 2026, 10:35 PM