GPT-5.2 wins reasoning. Gemini 3 wins creative. Claude wins coding. Why picking one model is now a mistake.
any updated thoughts with the 5.4, 4.6 and 3.1 model releases?
Maybe not about Gemini(not my vibes), but Opus and GPT, yes.
Opus → https://thoughts.jock.pl/p/opus-4-6-agent-experiment-2026?utm_source=publication-search
any updated thoughts with the 5.4, 4.6 and 3.1 model releases?
Maybe not about Gemini(not my vibes), but Opus and GPT, yes.
Opus → https://thoughts.jock.pl/p/opus-4-6-agent-experiment-2026?utm_source=publication-search