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
Multiple Llms
3
Incidents
3.8
Avg Severity
0
Critical
0
High
Top Failure Modes
Hallucination
3
Worst Incident
STUPID-2026-0033 6.4/10Slopsquatting: LLMs hallucinate package names attackers pre-register (react-codeshift, unused-imports)
Comparison Summary
| Metric | Claude Code | Multiple Llms |
|---|---|---|
| Total Incidents | 8 | 3 |
| Avg Severity | 6.4/10 | 3.8/10 |
| Critical Incidents | 3 | 0 |
| Top Failure Mode | Destructive Action | Hallucination |
Frequently Asked Questions
Is Claude Code or Multiple Llms more reliable?
Based on StupidLLM data, Claude Code has 8 documented failures (avg severity 6.4/10) while Multiple Llms has 3 (avg severity 3.8/10). Multiple Llms shows better reliability based on average severity scores.
What are the main differences between Claude Code and Multiple Llms failures?
Claude Code's most common failure mode is destructive action, while Multiple Llms most commonly fails via hallucination. Claude Code has 3 critical incidents vs Multiple Llms's 0.