LMArena
community
AI & ML interests
None defined yet.
Recent Activity
Organization Card
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 lmarena.ai, and see rankings at lmarena.ai/leaderboard.
Collections
1
spaces
6
Running
4.13k
Chatbot Arena Leaderboard
π
Display chatbot leaderboard and results
Running
52
Arena Hard
π¦Ύ
Compare model answers to questions
Running
9
Category Arena Example
π
Browse chatbot responses to compare models
Running
5
Preference Proxy Evaluations
π¦
Preference Proxy Evaluations
Running
188
Chatbot Arena
π¬
Initiate conversations with multiple chatbots
Running
39
Gpt-4o-mini Battles
π’
Filter and display conversations between models
models
20
lmarena-ai/p2l-7b-grk-01112025
Updated
β’
29
β’
3
lmarena-ai/p2l-7b-grk-02222025
Updated
β’
175
β’
4
lmarena-ai/p2l-0.5b-bt-01132025
Updated
β’
44
lmarena-ai/p2l-1.5b-bt-01132025
Updated
β’
22
lmarena-ai/p2l-3b-bt-01132025
Updated
β’
12
lmarena-ai/p2l-7b-bt-01132025
Updated
β’
14
β’
1
lmarena-ai/p2l-135m-bt-01132025
Updated
β’
80
lmarena-ai/p2l-360m-bt-01132025
Updated
β’
11
lmarena-ai/p2l-135m-rk-01132025
Updated
β’
14
lmarena-ai/p2l-360m-rk-01132025
Updated
β’
12
datasets
19
lmarena-ai/repochat-arena-preference-4k
Viewer
β’
Updated
β’
3.84k
β’
174
β’
1
lmarena-ai/arena-human-preference-100k
Viewer
β’
Updated
β’
106k
β’
1.06k
β’
35
lmarena-ai/VisionArena-Chat
Viewer
β’
Updated
β’
199k
β’
629
β’
1
lmarena-ai/webdev-arena-preference-10k
Viewer
β’
Updated
β’
10.5k
β’
33
β’
3
lmarena-ai/VisionArena-Battle
Viewer
β’
Updated
β’
29.8k
β’
207
β’
4
lmarena-ai/categories-benchmark-eval
Preview
β’
Updated
β’
10
β’
3
lmarena-ai/notebook-data-vision-arena-battle
Updated
β’
71
lmarena-ai/vision-arena-bench-v0.1
Viewer
β’
Updated
β’
500
β’
545
β’
1
lmarena-ai/Llama-3-70b-battles
Viewer
β’
Updated
β’
1.6k
β’
110
β’
3
lmarena-ai/PPE-MBPP-Plus-Best-of-K
Viewer
β’
Updated
β’
507
β’
103
β’
1