Comparisons / Claude Code vs OpenAI Codex
AI coding tools · HN opinions Nov 2025 – Nov 2026
Claude Code vs OpenAI Codex: what developers actually say
Based on 5,039 opinions on Hacker News from developers who discussed these two, most of them first-hand users.
Codex comes out ahead overall. It posts 69% approval against 54% for Claude Code, 63% against 51% over the last 90 days, and 181 commenters picked it over Claude Code versus 62 the other way. Codex also leads on net sentiment for cost, usage limits, code quality, UX, and reliability. Claude Code keeps edges on autonomy (+192 net versus +123) and speed (+81 versus +63), so choose it when the subagent and plugin workflow matters more than quota headroom.
When developers explicitly said they prefer one or switched: 62 picked Claude Code, 181 picked OpenAI Codex.
Choose Claude Code if
- Want a mature subagent and plugin ecosystem
- Value Claude Code's terminal interface and permission flow
- Can absorb tighter usage limits for stronger autonomous runs
Choose OpenAI Codex if
- Need more useful work per dollar and fewer quota interruptions
- Want stronger code quality and review results
- Prefer a more stable harness with clearer progress display
Where each one wins and loses
PraiseComplaintsA = Claude CodeB = OpenAI Codex
UX
Code quality
Reliability
Autonomy
Cost & pricing
Usage limits
Customization
Speed
Why developers switched
Picked Claude Code
Says Claude Code has the better UX, while Codex chases mass-market design and suffers for it.HN comment · Oct 12, 2026
Reports Codex filled about 12 GB with old versions, and rates it worse than Claude Code on every metric.HN comment · Oct 12, 2026
Says Codex quality and reliability have declined, and its coding falls short of Claude Code with Opus.HN comment · Oct 7, 2026
Says Codex cloud agents force you onto your own machine, while Claude Code works better as a cloud dev environment.HN comment · Sep 25, 2026
Says a Claude subscription lasts longer than Codex on the same projects, and produced more merged code.HN comment · Sep 22, 2026
Says Codex burns through limits, writes odd code, and lacks Claude Code's visibility into subagent work.HN comment · Sep 22, 2026
Picked OpenAI Codex
Says Opus drains a weekly quota in a day or two while Codex keeps running, and finds more flaws in Claude's commits.HN comment · Oct 29, 2026
Switched from Claude to Codex because the Claude Code harness feels unstable and frustrating.HN comment · Oct 14, 2026
Picks Codex for more generous usage limits and resets, plus unmetered ChatGPT access on the 20x plan.HN comment · Sep 22, 2026
Calls Claude Code's terminal interface buggy, clunky and slow, and prefers Codex's progress display and side chats.HN comment · Sep 20, 2026
Moved from Claude Code to Codex for better return on spend and better code quality.HN comment · Sep 20, 2026
Says Claude Code weakens CLAUDE.md instructions with a relevance disclaimer, while Codex follows AGENTS.md more faithfully.HN comment · Sep 19, 2026
Summaries are paraphrased. Each links to the original comment.