Amazon Q
1
Incidents
10.0
Avg Severity
1
Critical
0
High
Top Failure Modes
Security Vulnerability
1
Worst Incident
STUPID-2026-0035 10/10Hacker slipped a data-wiping prompt into Amazon Q's VS Code extension, shipped to ~1M installs
Claude Code
8
Incidents
6.4
Avg Severity
3
Critical
2
High
Top Failure Modes
Destructive Action
3
Other
2
Security Vulnerability
2
Worst Incident
STUPID-2026-0003 10/10Claude Code ran rm -rf on test fixtures thinking they were temp files
Comparison Summary
| Metric | Amazon Q | Claude Code |
|---|---|---|
| Total Incidents | 1 | 8 |
| Avg Severity | 10.0/10 | 6.4/10 |
| Critical Incidents | 1 | 3 |
| Top Failure Mode | Security Vulnerability | Destructive Action |
Frequently Asked Questions
Is Amazon Q or Claude Code more reliable?
Based on StupidLLM data, Amazon Q has 1 documented failures (avg severity 10.0/10) while Claude Code has 8 (avg severity 6.4/10). Claude Code shows better reliability based on average severity scores.
What are the main differences between Amazon Q and Claude Code failures?
Amazon Q's most common failure mode is security vulnerability, while Claude Code most commonly fails via destructive action. Amazon Q has 1 critical incidents vs Claude Code's 3.