Revision History
Reasoning (artificial intelligence) · 9 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 Claude 3.7 Sonnet release date (February 24, 2025), DeepSeek-R1's training description (pure RL applies to R1-Zero), an unsupported o4-mini performance claim, the Gemini Deep Think entry that mixed in February 2026 results, a 2024 IMO comparison (silver, not gold), MYCIN and DENDRAL dates, and a citation to an unrelated ICLR paper; date-qualified Humanity's Last Exam scores and o1's consensus-only benchmark numbers (plus 17 minor fixes)
Version 9 · Nov 2, 2026, 09:48 AM
- Added 6 contextual internal links
Version 8 · Jul 23, 2026, 03:04 PM