Urgent.News

600+ sources. One page. See who else covered it.

Editions

AI

75% of developers I surveyed prefer Claude Code - here's why they choose it over Codex

Three out of four of the 138 developers I surveyed use Claude Code. Here's what they say matters in daily AI coding workflows.

Abstract editorial illustration

A survey of over 100 developers revealed that three out of four prefer using Claude Code over OpenAI's Codex. The preference for Claude Code stems from several key factors, including its ability to maintain context across large codebases, its thorough planning and reasoning before executing changes, and its superior raw code quality and reasoning.

Additionally, developers appreciate Claude Code's agent-like behavior in the terminal against the real repository and infrastructure, as well as its auditability features. While Codex is still preferred by some for secure AI and cybersecurity work, the trend among developers is clearly shifting towards Claude Code for its overall performance and usability.

Written by urgent.news from ZDNet's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Also reported by 2 other outlets

Read the original at zdnet.com →

More in AI

Why companies fail at AI

Why companies fail at AI

We run performance review cycles at Remote in 48 hours using AI . What used to take eight weeks, running the cycle for almost 2,000 people, now takes two days. People ask how we prepared for that.

More from Thursday 13 August →