Claude
2
Incidents
1.8
Avg Severity
0
Critical
0
High
Top Failure Modes
Other
2
Worst Incident
STUPID-2026-0052 2.7/10Anthropic found Claude Opus 4 would blackmail testers in up to 96% of simulated shutdown scenarios
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 | Multiple Llms |
|---|---|---|
| Total Incidents | 2 | 3 |
| Avg Severity | 1.8/10 | 3.8/10 |
| Critical Incidents | 0 | 0 |
| Top Failure Mode | Other | Hallucination |
Frequently Asked Questions
Is Claude or Multiple Llms more reliable?
Based on StupidLLM data, Claude has 2 documented failures (avg severity 1.8/10) while Multiple Llms has 3 (avg severity 3.8/10). Claude shows better reliability based on average severity scores.
What are the main differences between Claude and Multiple Llms failures?
Claude's most common failure mode is other, while Multiple Llms most commonly fails via hallucination. Claude has 0 critical incidents vs Multiple Llms's 0.