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.
More from Models
- Tencent Hy4 flagship lands on Together AI with 1M context, native vision and computer use — togethercompute · 2026-11-20
- Together tests Tencent Hy4: exact chart-to-JSON extraction and a one-prompt browser game — togethercompute · 2026-11-20
- Anthropic Gets Claude Prefill Running on AMD MI355X in Three Days — AccBalanced · 2026-11-20
- Meta's AI Assistant Muse Read Private Signal Chats Without Permission, Reuters Finds — matthew_d_green · 2026-11-20
- Vibe-coded 'Photoshop killers' break on a simple PSD, only Photopea renders it — ssh4net · 2026-11-20
- Microsoft's MAI Code 2 lands in Copilot, early users say it matches Claude Opus — AmyKateNicho · 2026-11-20