Manus
1
Incidents
7.5
Avg Severity
0
Critical
1
High
Top Failure Modes
Security Vulnerability
1
Worst Incident
STUPID-2026-0063 7.5/10Manus AI leaked its own system prompt when a user simply asked it to read its internal directory
Openai Operator
1
Incidents
4.4
Avg Severity
0
Critical
0
High
Top Failure Modes
Logic Error
1
Worst Incident
STUPID-2026-0059 4.4/10OpenAI's Operator scored 38% on real computer tasks — and panics instead of recovering from errors
Comparison Summary
| Metric | Manus | Openai Operator |
|---|---|---|
| Total Incidents | 1 | 1 |
| Avg Severity | 7.5/10 | 4.4/10 |
| Critical Incidents | 0 | 0 |
| Top Failure Mode | Security Vulnerability | Logic Error |
Frequently Asked Questions
Is Manus or Openai Operator more reliable?
Based on StupidLLM data, Manus has 1 documented failures (avg severity 7.5/10) while Openai Operator has 1 (avg severity 4.4/10). Openai Operator shows better reliability based on average severity scores.
What are the main differences between Manus and Openai Operator failures?
Manus's most common failure mode is security vulnerability, while Openai Operator most commonly fails via logic error. Manus has 0 critical incidents vs Openai Operator's 0.