We're releasing the full history of Arena leaderboard data as a public dataset, nearly 3 years of rankings across 10 Arenas, dozens of categories, and hundreds of models. Optimized to empower analysis and unlock new insights across modalities and over time. Check out some examples of how to use the data in thread.
We're excited to see what the community finds. Dig in and share what you discover. More info in thread.
3 Replies
5 Retweets
61 Likes
4,272 Views 
One Sentence Summary
LMArena releases three years of historical leaderboard data as a public dataset to empower community research and analysis.
Summary
LMArena has released a comprehensive dataset covering three years of leaderboard rankings across 10 arenas, dozens of categories, and hundreds of models. This release is designed to enable researchers and the community to perform deep analysis on model performance trends over time.
AI Score
87
Influence Score 12
Published At Yesterday
Language
English
Tags
LMSYS
Dataset
Open Data
AI Benchmarking