LM Arena Accused of Unfair Rankings
This is a Gemini news story, published by Ars Technica, that relates primarily to UC Berkeley news.
Gemini news
For more Gemini news, you can click here:
more Gemini newsNews about Ai research
For more Ai research news, you can click here:
more Ai research newsArs Technica news
For more news from Ars Technica, you can click here:
more news from Ars TechnicaAbout the Otherweb
Otherweb, Inc is a public benefit corporation, dedicated to improving the quality of news people consume. We are non-partisan, junk-free, and ad-free. We use artificial intelligence (AI) to remove junk from your news feed, and allow you to select the best tech news, business news, entertainment news, and much more. If you like this article about Ai research, you might also like this article about
Chatbot Arena. We are dedicated to bringing you the highest-quality news, junk-free and ad-free, about your favorite topics. Please come every day to read the latest AI chatbots news, AI market news, news about Ai research, and other high-quality news about any topic that interests you. We are working hard to create the best news aggregator on the web, and to put you in control of your news feed - whether you choose to read the latest news through our website, our news app, or our daily newsletter - all free!
Chatbot Arena APIArs Technica
•Technology
Technology
New study accuses LM Arena of gaming its popular AI benchmark

84% Informative
LM Arena was created in 2023 as a research project at UC Berkeley .
Users feed a prompt into two AI models in the "Chatbot Arena" and evaluate the output to vote on the one they like more.
This data is aggregated in the leaderboard that shows which models people like the most.
Google 's Gemini 2.5 Pro debuted at the top of the LM Arena leaderboard this year .
VR Score
88
Informative language
90
Neutral language
50
Article tone
formal
Language
English
Language complexity
52
Offensive language
not offensive
Hate speech
not hateful
Attention-grabbing headline
not detected
Known propaganda techniques
not detected
Time-value
medium-lived
External references
2
Source diversity
2
Affiliate links
no affiliate links