Devin vs Manus
AI Agent Reliability Comparison
According to StupidLLM's incident database of 64 documented AI agent failures, Devin has 12 incidents (avg severity 4.9/10) while Manus has 1 (avg severity 7.5/10). Here's how these two AI coding agents compare on reliability, failure modes, and real-world risk.
Devin
Top Failure Modes
Worst Incident
STUPID-2026-0001 10/10Manus
Top Failure Modes
Worst Incident
STUPID-2026-0063 7.5/10Comparison Summary
| Metric | Devin | Manus |
|---|---|---|
| Total Incidents | 12 | 1 |
| Avg Severity | 4.9/10 | 7.5/10 |
| Critical Incidents | 3 | 0 |
| Top Failure Mode | Scope Explosion | Security Vulnerability |
Frequently Asked Questions
Is Devin or Manus more reliable?
Based on StupidLLM's incident database, Devin has 12 documented failures (avg severity 4.9/10) while Manus has 1 (avg severity 7.5/10). Devin shows better reliability based on average severity scores.
What are the main differences between Devin and Manus failures?
Devin's most common failure mode is scope explosion, while Manus most commonly fails via security vulnerability. Devin has 3 critical incidents vs Manus's 0.
Which has more critical-severity failures?
Devin has more critical failures (3 vs 0), indicating a higher likelihood of severe, production-impacting incidents.
What is the most dangerous failure mode for Devin?
Devin's most frequent failure mode is scope explosion — its worst documented incident (STUPID-2026-0001) was rated 10/10 severity. Understanding these failure patterns helps teams decide whether Devin is safe for their specific use case.
What is the most dangerous failure mode for Manus?
Manus's most frequent failure mode is security vulnerability — its worst documented incident (STUPID-2026-0063) was rated 7.5/10 severity. Understanding these failure patterns helps teams decide whether Manus is safe for their specific use case.
Should I use Devin or Manus for production code?
Based on StupidLLM's reliability data, Devin has a lower average failure severity (4.9/10 vs 7.5/10), making it the statistically safer choice for production environments. However, both agents have documented critical incidents — no AI coding agent is risk-free.
How many verified incidents does each agent have?
Devin has 12 verified incidents out of 12 total, while Manus has 1 verified out of 1. Verified incidents are confirmed against source evidence (GitHub PRs, bug reports, news articles), making them the most reliable data points in StupidLLM's database.
How does Devin compare to other AI agents?
StupidLLM tracks 27 AI coding agents. Devin has 12 documented failures — placing it in the mid-range for reliability. See the full comparison matrix for context against all tracked agents.
How does Manus compare to other AI agents?
StupidLLM tracks 27 AI coding agents. Manus has 1 documented failures — placing it among the higher-risk agents in the database. See the full comparison matrix for context against all tracked agents.