Revision History
OSWorld · 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.
- Link Claude Fable 5.1 and Claude Mythos 5.1 to their new pages
Version 8 · Sep 4, 2026, 03:53 AM
- Add OSWorld 2.0 section (108 long-horizon tasks, partial vs binary scoring, v2026.06.24 and v2026.08.08 releases, 82-task offline set, official leaderboard as of 3 September 2026) and the September 2026 vendor results: GPT-6 Astra 72.6% partial on the offline set with OpenAI's 40-vs-75-minute latency claim and footnote, Claude Fable 5.1 77.9%/41.7% with Anthropic's non-comparability caveat; Astra not on the official leaderboard as of 3 September 2026
Version 7 · Sep 4, 2026, 02:46 AM
- Added 6 contextual internal links
Version 6 · Jul 23, 2026, 03:30 PM