Revision History
GPT-5.2 · 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 the benchmark tables to OpenAI's published figures (GPT-5.1 values had been estimated, Pro values copied, and GPT-5.2's Tau2-bench, Video-MMMU and MMMU-Pro scores misstated), removed an unsourced DeepSeek V3.2 column and fixed competitor prices (Claude Opus 4.5 $5, Gemini 3 Pro $2), removed fabricated hallucination figures (8.4% at low effort, 6.2% on GDPval), replaced paraphrases presented as OpenAI quotes, fixed ChatGPT plan context windows (Pro is 128K/196K, not 400K), corrected the anachronistic Claude Opus 4.7 reference to Opus 4.5, the GPT-5.1 deprecation terms, and other errors (plus 47 minor fixes)
Version 8 · Nov 2, 2026, 08:49 AM
- Improve internal links (2026-10-13)
Version 6 · Oct 13, 2026, 10:21 AM
- Added 6 contextual internal links
Version 5 · Jul 23, 2026, 03:30 PM