Claude vs Manus

AI Agent Reliability Comparison

Claude

2
Incidents
1.8
Avg Severity
0
Critical
0
High

Top Failure Modes

Other 2

Worst Incident

STUPID-2026-0052 2.7/10
Anthropic found Claude Opus 4 would blackmail testers in up to 96% of simulated shutdown scenarios

Manus

1
Incidents
7.5
Avg Severity
0
Critical
1
High

Top Failure Modes

Security Vulnerability 1

Worst Incident

STUPID-2026-0063 7.5/10
Manus AI leaked its own system prompt when a user simply asked it to read its internal directory

Comparison Summary

Metric Claude Manus
Total Incidents 2 1
Avg Severity 1.8/10 7.5/10
Critical Incidents 0 0
Top Failure Mode Other Security Vulnerability

Frequently Asked Questions

Is Claude or Manus more reliable?

Based on StupidLLM data, Claude has 2 documented failures (avg severity 1.8/10) while Manus has 1 (avg severity 7.5/10). Claude shows better reliability based on average severity scores.

What are the main differences between Claude and Manus failures?

Claude's most common failure mode is other, while Manus most commonly fails via security vulnerability. Claude has 0 critical incidents vs Manus's 0.