Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
Prompt-to-Leaderboard (P2L)github.com · Low evidencePrompt to Leaderboard (P2L) is a method that trains a large language model to generate prompt-specific leaderboards by predicting human preference votes. It enables unsupervised task-specific evaluation, optimal model routing, and personalization, achieving the #1 spot on the Chatbot Arena leaderboard in January 2025.
Parse Score