Head to head

Claude vs Codex

Comparing 3 documented Claude incidents against 3 for Codex.

Verdict

Claude has the lower average failure severity (3.6/10 vs 5.8/10), making it the statistically safer choice of the two — though both agents have documented critical incidents.

Reliability metrics for Claude and Codex
MetricClaudeCodex
Documented incidents33
Average severity3.65.8
Critical00
High11
Verified32

Severity at a glance

Claude
3.6low
Codex
5.8medium

Failure modes

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

The incidents behind these numbers