tech
February 6, 2026
Vibe Check: Opus 4.6—The Best Coding Model We’ve Tested (With Some Maddening Habits)
It one-shotted a problem other models missed—and brings agentic, parallel work to non-coding tasks
.png)
TL;DR
- Opus 4.6 is the best AI coder tested, solving a real iOS coding task that stumped GPT-5.3 Codex and Opus 4.5.
- It is more thorough, explores context more carefully, and is smarter than Opus 4.5, excelling in coding and professional work.
- Features include "Adaptive Thinking" and agentic capabilities for parallel work and autonomous actions.
- While improved for writing and editing, Opus 4.6 can be more verbose, slower, and prone to AI-isms than its predecessor.
- Users report occasional maddening errors, unexpected changes, and unreliability despite its advanced capabilities.
Continue reading
the original article