Head to head

Claude Code vs Codex

Comparing 24 documented Claude Code incidents against 3 for Codex.
Full Claude Codereport →Full Codexreport →

Verdict

Codex has the lower average failure severity (5.8/10 vs 7.4/10), making it the statistically safer choice of the two — though both agents have documented critical incidents.

Reliability metrics for Claude Code and Codex
MetricClaude CodeCodex
Documented incidents243
Average severity7.45.8
Critical90
High91
Verified232

Severity at a glance

Claude Code
7.4high
Codex
5.8medium

Failure modes

Claude Code
Distribution of failure modes across all documented incidents.
Codex
Distribution of failure modes across all documented incidents.

The incidents behind these numbers

Claude Code

10.0Claude Code wiped DataTalks.Club's production infrastructure — 2.5 years of course data — during an AWS migration10.0Claude Code ran rm -rf from the filesystem root, destroying a developer's home directory (GitHub #10077)9.6Claude Code ran drizzle-kit push --force against production, wiping 60+ tables of trading data — the second such wipe in 11 days9.5Claude Code moved files into a log/ subfolder, then rm -rf'd the parent directory containing it — 1,500 files gone (GitHub #49129)9.5Claude Code's parallel-subagent worktree cleanup deleted the main .git directory and entire working tree — irrecoverable repo loss (GitHub #48927)

Codex

8.0OpenAI Codex wiped an entire hard drive after being asked to delete one old backup file (GitHub #11006)6.0OpenAI Codex ran "rm -rf *" and deleted an entire project after the user pressured it to stop pausing for safety checks (GitHub #6801)3.5OpenAI Codex deleted important project files with no explicit request or confirmation, exact command never captured (GitHub #38312)