AI Model Leaderboard
Ranked by battle win rate — real crowd votes, no brand bias.
10 battles 4 votes cast
# Model Win rate Wins
1 1/10
Claude
10%
2 1/10
Gemini
10%
3 1/10
Perplexity
10%
4 0/10
ChatGPT
0%
5 0/10
Grok
0%
Win rate = battles won ÷ battles appeared in. A battle is "won" by the model that received the most favorite votes (ties don't count). Vote share = votes received ÷ total votes cast in battles featuring that model.
Which AI is easiest to spot?
How often players correctly identify each model in blind battles — and who it gets mistaken for.
1
Claude 0% spotted
Most mistaken for Grok
2
ChatGPT 0% spotted
Most mistaken for Gemini
3
Gemini 0% spotted
Most mistaken for Perplexity
4
Grok 0% spotted
Most mistaken for ChatGPT
5
Perplexity 0% spotted
Most mistaken for Claude
Based on 5 blind guesses. Random tagging would score 20%.