Last updated: April 5, 2026 · Evaluation & Benchmarks · by Daniel Ashford

What is Arena Elo Rating?

QUICK ANSWER

A crowdsourced model ranking based on human preference votes in blind comparisons.

Definition

Arena Elo is a rating system used by the LMSYS Chatbot Arena to rank language models based on human preference. Users compare two anonymous model outputs side-by-side and vote for the better one. Preferences are aggregated using the Elo rating system.

How It Works

The Chatbot Arena has collected over 6 million human votes. Arena Elo captures something benchmarks often miss: subjective quality, helpfulness, and user preference. However, it is influenced by the user population and types of questions asked.

Example

Claude Opus 4 holds Arena Elo #1 at approximately 1342, meaning it wins pairwise comparisons against most other models.

Related Terms

Benchmark
A standardized test used to measure and compare LLM capabilities.
LLM Judge Index™
Our proprietary composite score ranking LLMs across 6 evaluation dimensions on a 0-100 scale.

See How Models Compare

Understanding arena elo rating is important when choosing the right AI model. See how 12 models compare on our leaderboard.

View Leaderboard →Our Methodology
← Browse all 47 glossary terms
DA
Daniel Ashford
Founder & Lead Evaluator · 200+ models evaluated