Coding skill is multidimensional: no single 'best at coding' model

sandersted · x · 2026-11-20

Argues coding is highly multidimensional—one model wins at frontend, another at review—so 'better at coding' collapses poorly. His take: OpenAI wasn't far ahead in 2022-2025 (Opus 3/Sonnet 3.5 beat GPT in many ways) and Anthropic wasn't ahead in 2026 (GPT 5.2+/6.2 beat Claude); both won outsized share via first-mover advantage.

Original post →

More from Models

Models channel →