OpenClaw vs Hermes: One Chart Is Lying To You #shorts

A comparison between OpenClaw and Hermes models highlighting a discrepancy in how their performance metrics are measured. The video suggests that one chart may be misleading because different metrics (GitHub stars vs OpenRouter tokens) are being used to evaluate the models, making direct comparison problematic. This is a cautionary tale about metric selection and data visualization in AI model evaluation.

Key Points

• •OpenClaw and Hermes use different success metrics that aren't directly comparable
• •GitHub stars measure community adoption/popularity, not necessarily model performance
• •OpenRouter tokens measure actual API usage and real-world deployment
• •Visual comparisons can be misleading when underlying metrics differ
• •When comparing AI models, verify what each metric actually measures
• •Popularity (stars) doesn't always correlate with practical utility (token usage)
• •Be skeptical of charts comparing different measurement units or methodologies

Workflow Diagram

Concepts