In-the-wild Interactions with Search-LLMs w/ Human Preferences
Arena
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards
AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment
Organization Card
Arena (formerly LMArena) is an open platform for crowdsourced AI benchmarking, originally created by researchers from UC Berkeley SkyLab.
We have officially graduated from LMSYS.org!
Free chat with the best AI models at arena.ai, and see rankings at arena.ai/leaderboard.
spaces 9
Running
5.04k
Arena Leaderboard
🏆
View the LMArena AI model leaderboard
Running
277
Chatbot Arena
💬
View the LMArena text model leaderboard
Running
Agents
10
Arena Hard Viewer
⚡
Browse and view model judgments in benchmarks
Running
Agents
31
Llama-4-Maverick-03-26-Experimental Battles
🔥
Display and filter chat conversations between models
Sleeping
Agents
3
Prompt Freshness
😻
Filter prompts based on similarity and language
models 20
lmarena-ai/p2l-7b-grk-01112025
7B • Updated • 25 • 5
lmarena-ai/p2l-7b-grk-02222025
7B • Updated • 26 • 7
lmarena-ai/p2l-0.5b-bt-01132025
0.5B • Updated • 29
lmarena-ai/p2l-1.5b-bt-01132025
2B • Updated • 30
lmarena-ai/p2l-3b-bt-01132025
3B • Updated • 13
lmarena-ai/p2l-7b-bt-01132025
7B • Updated • 19 • 2
lmarena-ai/p2l-135m-bt-01132025
0.1B • Updated • 31 • 3
lmarena-ai/p2l-360m-bt-01132025
0.4B • Updated • 22
lmarena-ai/p2l-135m-rk-01132025
0.1B • Updated • 15
lmarena-ai/p2l-360m-rk-01132025
0.4B • Updated • 23
datasets 26
lmarena-ai/leaderboard-dataset
Viewer • Updated • 2.62M • 277k • 43
lmarena-ai/Arena-T2I-Training
Viewer • Updated • 992 • 204
lmarena-ai/Arena-T2I-Hard
Viewer • Updated • 310 • 224 • 1
lmarena-ai/search-arena-24k
Viewer • Updated • 24.1k • 1.32k • 42
lmarena-ai/arena-expert-5k
Viewer • Updated • 5.13k • 702 • 20
lmarena-ai/arena-human-preference-140k
Viewer • Updated • 136k • 8.03k • 62
lmarena-ai/arena-hard-auto
Updated • 3.92k • 8
lmarena-ai/categories-benchmark-eval
Preview • Updated • 51 • 6
lmarena-ai/search-arena-v1-7k
Viewer • Updated • 7k • 323 • 28
lmarena-ai/webdev-arena-preference-10k
Viewer • Updated • 10.5k • 1.7k • 23