Revision History
Qwen3 · 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 benchmark tables whose competitor scores (DeepSeek-R1, o3-mini, GPT-4o, Gemini 2.5 Pro) and Qwen3-32B scores did not match the Qwen3 technical report, including a false claim that Qwen3 doubled DeepSeek-R1 and beat GPT-4o on BFCL; fixed native context lengths, the distillation stage and teachers, Qwen3-Omni language counts, the Thinking-2507 release date and AIME 2025 ranking versus o4-mini, Qwen3-32B API pricing, Qwen3-Coder-Next's release month, the Kimi K2 license terms, the 2026 open-model comparison (DeepSeek V4, GLM-5.1, Gemma 4 licenses and scores), and other errors (plus 49 minor fixes)
Version 10 · Nov 2, 2026, 04:29 AM
- Improve internal links (2026-10-13)
Version 8 · Oct 13, 2026, 10:20 AM
- Added 6 contextual internal links
Version 7 · Jul 23, 2026, 03:29 PM
- Pre-update snapshot before enhancement to 9304 words.
Version 4 · May 18, 2026, 04:23 AM