Autogpt vs Devin

AI Agent Reliability Comparison

Autogpt

1
Incidents
2.9
Avg Severity
0
Critical
0
High

Top Failure Modes

Infinite Loop 1

Worst Incident

STUPID-2026-0010 2.9/10
AutoGPT spent $450 on API calls trying to build a todo app

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

Comparison Summary

Metric Autogpt Devin
Total Incidents 1 12
Avg Severity 2.9/10 4.9/10
Critical Incidents 0 3
Top Failure Mode Infinite Loop Scope Explosion

Frequently Asked Questions

Is Autogpt or Devin more reliable?

Based on StupidLLM data, Autogpt has 1 documented failures (avg severity 2.9/10) while Devin has 12 (avg severity 4.9/10). Autogpt shows better reliability based on average severity scores.

What are the main differences between Autogpt and Devin failures?

Autogpt's most common failure mode is infinite loop, while Devin most commonly fails via scope explosion. Autogpt has 0 critical incidents vs Devin's 3.