The End of the One-Model Era: Building My…

Jan 15

GPT-5.2 wins reasoning. Gemini 3 wins creative. Claude wins coding. Why picking one model is now a mistake.

2 Comments

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

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts