Revision History
BIG-Bench · 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 BIG-Bench Extra Hard results table, which credited GPT-4o with the best general-purpose score; the paper's best general-purpose model was Gemini 2.0 Flash (9.8% harmonic mean, 23.9% micro average) (plus 14 minor fixes)
Version 10 · Nov 4, 2026, 05:19 PM
- References: renumbered 1 hidden reference so they show and link
Version 9 · Oct 30, 2026, 09:46 AM
- Improve internal links (2026-10-13)
Version 8 · Oct 13, 2026, 10:09 AM
- Added 6 contextual internal links
Version 7 · Jul 23, 2026, 03:05 PM
- Pre-update snapshot before enhancement to 4293 words.
Version 5 · May 18, 2026, 10:51 AM