Arena.ai

Formerly LMArena, Arena.ai (UC Berkeley origins) runs crowdsourced, blind head-to-head model evaluations across text, code, image, and video. Rankings use Bradley-Terry scoring over 250M+ real conversations. Offers commercial eval services for labs and enterprises, plus Max, a community-vote-powered model router.

Last 12 months

Focus areas

BENCHMARKS•IMAGE•LLMS•TOOL USE•VIDEO GENERATION•VIDEO UNDERSTANDING

Links

Google DeepMind's Gemini 4 Carbon Tops LM Arena's Text Leaderboard at 72% Less

Arena.aiBenchmarks

Oct 30

Arena's Agent Mode Now Connects GitHub, Linear, Vercel and 6 More Developer Tools

Oct 27

LM Arena's Max Router Matches Claude While Cutting Agent Costs by 37%

Arena.aiBenchmarks

Oct 16

LM Arena's Max Router Tops Agent Benchmarks While Cutting Costs 37.5%

Oct 13

Arena.ai Crowns Claude Opus 5.5 After Rewriting Its Agent Shell Reliability Test

Arena.aiBenchmarks

Oct 13

Jev Router Wins on Steerability but Costs 38% More Than Direct Calls

Oct 07

Arena's FLUX.2-dev Beats Every Open-Source Image Model With 66% Win Rate

Oct 02

LM Arena Merges 12 AI Leaderboards Into One Free Dashboard

Arena.aiBenchmarks

Sep 24

Agent Arena Splits Into 3 Categories, Proving No Single Model Wins

Arena.aiBenchmarks

Aug 17

LM Arena Proves Claude Opus 5 Writes 3x More but Simpler

Aug 12