Codex vs. Claude Code on the Same Tasks: Equal Quality, 2.4x Cost Gap
Understand the story
On October 6, 2026, a DEV Community author published a head-to-head test of Codex and Claude Code on the same tasks. The test ran on the python-humanize repository and covered four tasks: fixing a bug from a real issue, adding a feature to spec, refactoring with no behavior change, and reviewing code with 3 planted bugs. Each task was run twice. The versions used were Claude Code 2.1.291 (claude-opus-5-5) and Codex CLI 0.160.0 (gpt-6.1-sol). All 16 runs passed the checks, and all four code reviews found all 3 planted bugs with no false positives, so quality was a tie; the author’s conclusion is that Codex costs 2.4 times less.
Generated by AI from reports · Updated 6 hours ago
Report timeline
Follow the reports to explore different perspectives.
- DEV Community · CodexCodex 与 Claude Code 同任务实测：质量打平，Codex 成本低 2.4 倍
作者在 python-humanize 仓库上用四个任务（真实 issue 修 bug、按规格加功能、无行为变更重构、带 3 个植入 bug 的代码评审）各跑两遍，Claude Code 2.1.291（claude-opus-5-5）与 Codex CLI 0.160.0（gpt-6.1-sol）16 次运行全部通过检查，四个评审都找齐 3 个植入 bug 且无误报。
Interest in this story
Current interest 8·Peak within comparable coverage 10（Oct 6, 19:00）·Change over 24 hours within comparable coverage –
The trend compares the same participants under continuous, complete observation, so its coverage may be narrower than the current score. Hover or tap to view hourly interest; use the left and right arrow keys to navigate.