AI Ranks AI

What Happens When Chatbots Judge Each Other

A new study asked ChatGPT, Claude, Gemini, Perplexity and Grok to rank one another. The results reveal hidden pecking orders.

The Study

Second Wind Ran 360 Probes On Five Models

Published March 2026, the analysis used forced comparisons, open prompts and exclusion tests to map how AI models see their rivals.

The Numbers

ChatGPT Wins Default Status By A Mile

ChatGPT ranks first 68.8% of the time and gets mentioned 88.5% of the time. Claude leads reasoning. Perplexity owns research but gets boxed in.

The Catch

Being The Best At One Thing Isn't Enough

Perplexity's niche-boxing rate hit 55.8%. Specialists get praised for narrow tasks but skipped when questions are broad and general.

The Pattern

AI Recommendations Now Feed Themselves

Models reinforce each other's reputations, creating a feedback loop that decides which AI gets suggested to millions of daily users.

Read More

See The Full Breakdown Of Every Model

Get the complete rankings, scores and quotes behind ChatGPT, Claude, Gemini and Perplexity's roles in the full article.