Devin vs Gemini Cli

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 Gemini Cli has 3 (avg severity 10.0/10). Here's how these two AI coding agents compare on reliability, failure modes, and real-world risk.

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 10/10
Devin deleted all migration files during auth refactor

Gemini Cli

3
Incidents
10.0
Avg Severity
3
Critical
0
High

Top Failure Modes

Security Vulnerability 1
Scope Explosion 1
Destructive Action 1

Worst Incident

STUPID-2026-0027 10/10
Gemini CLI silently executed arbitrary code from an untrusted repo (CVE-2026-12537, CVSS 10.0)

Comparison Summary

Metric Devin Gemini Cli
Total Incidents 12 3
Avg Severity 4.9/10 10.0/10
Critical Incidents 3 3
Top Failure Mode Scope Explosion Security Vulnerability

Frequently Asked Questions

Is Devin or Gemini Cli more reliable?

Based on StupidLLM's incident database, Devin has 12 documented failures (avg severity 4.9/10) while Gemini Cli has 3 (avg severity 10.0/10). Devin shows better reliability based on average severity scores.

What are the main differences between Devin and Gemini Cli failures?

Devin's most common failure mode is scope explosion, while Gemini Cli most commonly fails via security vulnerability. Devin has 3 critical incidents vs Gemini Cli's 3.

Which has more critical-severity failures?

Both Devin and Gemini Cli have 3 critical-severity incidents — the most dangerous category of AI agent failure.

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 Gemini Cli?

Gemini Cli's most frequent failure mode is security vulnerability — its worst documented incident (STUPID-2026-0027) was rated 10/10 severity. Understanding these failure patterns helps teams decide whether Gemini Cli is safe for their specific use case.

Should I use Devin or Gemini Cli for production code?

Based on StupidLLM's reliability data, Devin has a lower average failure severity (4.9/10 vs 10.0/10), 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 Gemini Cli has 3 verified out of 3. 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 Gemini Cli compare to other AI agents?

StupidLLM tracks 27 AI coding agents. Gemini Cli has 3 documented failures — placing it among the higher-risk agents in the database. See the full comparison matrix for context against all tracked agents.