Revision History
Qwen3-Max · 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.
- Correction: Corrected Qwen3-Max-Thinking benchmark figures that mixed heavy test-time-scaling results with standard scores (GPQA, LiveCodeBench, Humanity's Last Exam), the wrong Claude comparator (Opus 4.5, not 4.7), nonexistent model ID usage, a misquoted Alibaba blog line, a misstated Artificial Analysis ranking, a wrong GPT-5 price comparison and an unsupported 'QwenChineseBench' claim, and noted that Qwen3-Max has been succeeded by Qwen3.6-, 3.7- and 3.8-Max (plus 15 minor fixes)
Version 8 · Nov 5, 2026, 11:33 AM
- Update: fix version-number links (e.g. Claude 3.5 was linked as Claude 3 followed by .5)
Version 7 · Nov 5, 2026, 10:52 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:22 AM
- Linked artificial superintelligence to its article
Version 4 · Oct 8, 2026, 11:19 PM
- Added 6 contextual internal links
Version 3 · Jul 23, 2026, 03:30 PM