Revision History
HealthBench · 7 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.
- Link Claude Fable 5.1 and Claude Mythos 5.1 to their new pages
Version 7 · Sep 4, 2026, 03:53 AM
- Add GPT-6 Astra (September 3, 2026) HealthBench results: system card section 6 table for all four variants with per-benchmark length penalties, the launch-post HealthBench Professional cross-provider row with its footnote and the press-kit and later-page discrepancies, the dynamic mental health evaluations, and the HealthBench Professional length-adjustment method from the paper.
Version 6 · Sep 4, 2026, 02:51 AM
- Added 6 contextual internal links
Version 5 · Jul 23, 2026, 03:01 PM