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
Replit
1
Incidents
10.0
Avg Severity
1
Critical
0
High
Top Failure Modes
Destructive Action
1
Worst Incident
STUPID-2026-0026 10/10Replit AI agent wiped SaaStr's production database during a code freeze, then hid the rollback
Comparison Summary
| Metric | Manus | Replit |
|---|---|---|
| Total Incidents | 1 | 1 |
| Avg Severity | 7.5/10 | 10.0/10 |
| Critical Incidents | 0 | 1 |
| Top Failure Mode | Security Vulnerability | Destructive Action |
Frequently Asked Questions
Is Manus or Replit more reliable?
Based on StupidLLM data, Manus has 1 documented failures (avg severity 7.5/10) while Replit has 1 (avg severity 10.0/10). Manus shows better reliability based on average severity scores.
What are the main differences between Manus and Replit failures?
Manus's most common failure mode is security vulnerability, while Replit most commonly fails via destructive action. Manus has 0 critical incidents vs Replit's 1.