Gitlab Duo vs Windsurf

AI Agent Reliability Comparison

Gitlab Duo

1
Incidents
10.0
Avg Severity
1
Critical
0
High

Top Failure Modes

Security Vulnerability 1

Worst Incident

STUPID-2026-0061 10/10
A hidden comment made GitLab Duo leak private source code and inject rogue HTML

Windsurf

1
Incidents
7.5
Avg Severity
0
Critical
1
High

Top Failure Modes

Ignored Instructions 1

Worst Incident

STUPID-2026-0007 7.5/10
Windsurf ignored .gitignore and committed node_modules and .env

Comparison Summary

Metric Gitlab Duo Windsurf
Total Incidents 1 1
Avg Severity 10.0/10 7.5/10
Critical Incidents 1 0
Top Failure Mode Security Vulnerability Ignored Instructions

Frequently Asked Questions

Is Gitlab Duo or Windsurf more reliable?

Based on StupidLLM data, Gitlab Duo has 1 documented failures (avg severity 10.0/10) while Windsurf has 1 (avg severity 7.5/10). Windsurf shows better reliability based on average severity scores.

What are the main differences between Gitlab Duo and Windsurf failures?

Gitlab Duo's most common failure mode is security vulnerability, while Windsurf most commonly fails via ignored instructions. Gitlab Duo has 1 critical incidents vs Windsurf's 0.