Cursor
5
Incidents
6.1
Avg Severity
2
Critical
0
High
Top Failure Modes
Security Vulnerability
1
Destructive Action
1
Infinite Loop
1
Worst Incident
STUPID-2026-0029 10/10Malicious cloned repository triggered code execution in Cursor on Windows
Devin
12
Incidents
4.9
Avg Severity
3
Critical
0
High
Top Failure Modes
Scope Explosion
2
Destructive Action
2
Infinite Loop
2
Worst Incident
STUPID-2026-0001 10/10Devin deleted all migration files during auth refactor
Comparison Summary
| Metric | Cursor | Devin |
|---|---|---|
| Total Incidents | 5 | 12 |
| Avg Severity | 6.1/10 | 4.9/10 |
| Critical Incidents | 2 | 3 |
| Top Failure Mode | Security Vulnerability | Scope Explosion |
Frequently Asked Questions
Is Cursor or Devin more reliable?
Based on StupidLLM data, Cursor has 5 documented failures (avg severity 6.1/10) while Devin has 12 (avg severity 4.9/10). Devin shows better reliability based on average severity scores.
What are the main differences between Cursor and Devin failures?
Cursor's most common failure mode is security vulnerability, while Devin most commonly fails via scope explosion. Cursor has 2 critical incidents vs Devin's 3.