LMArena is now Arena
What began as a PhD research experiment to compare AI language models has grown over time into something broader, shaped by the people who use it.
Latest
Research
Studying the Frontier: Arena Expert
Arena Expert is a great way to differentiate between frontier models.
In this analysis, we compare how models perform on 'general' vs 'expert' prompts, focusing on 'thinking' vs 'non-thinking' models.
LMArena's Ranking Method
Arena Expert and Occupational Categories
Re-introducing Vision Arena Categories
Introducing BiomedArena.AI: Evaluating LLMs for Biomedical Discovery
A Deep Dive into Recent Arena Data
Does Sentiment Matter Too?
News
LMArena is now Arena
What began as a PhD research experiment to compare AI language models has grown over time into something broader, shaped by the people who use it.
Video Arena Is Live on Web
Fueling the World’s Most Trusted AI Evaluation Platform
LMArena's Ranking Method
The Next Stage of AI Coding Evaluation Is Here
