Elo

Elo is a rating system that estimates relative skill from head-to-head results and is also used to compare AI models.

2 articles
Last mentioned

Elo is a rating system that updates estimates of relative skill based on head-to-head outcomes and existing ratings. It was devised by the Hungarian-American physicist Arpad Elo to rate chess players and bears his name. Unlike a score based on fixed questions, an Elo rating is relative and depends on the pool of competitors and the judging method.

In AI, pairs of model responses are compared, a preferred answer is chosen, and the outcomes are converted into Elo ratings to rank models. Leaderboards such as LMArena, formerly Chatbot Arena, are well-known examples.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

On an Elo chart that plots performance against parameter count, the Gemma 4 26B and 31B thinking models score roughly 1440 to 1460.

An Elo score is a relative rating used to compare performance; a higher GDPVal-AA rating indicates a stronger result in that evaluation.


© 2026 AIPOST. All rights reserved.

AIPOST is an AI publication covering practical AI, AI security, performance, startups, health, ethics and industry news. No account is needed, and our privacy policy explains how we handle personal information.