II.
Benchmark overview
Reference · livebenchmark:lmsys-arena
Chatbot Arena (LMSYS) overview
Chatbot Arena (LMSYS / LMArena) is a crowdsourced LLM evaluation platform that ranks models via blinded pairwise human votes, producing an Elo-style leaderboard.
Attributes
displayName
Chatbot Arena (LMSYS)
homepageUrl
kind
agent-leaderboard
targetsKind
ModelVersion
description
Chatbot Arena (LMSYS / LMArena) is a crowdsourced LLM evaluation
platform that ranks models via blinded pairwise human votes,
producing an Elo-style leaderboard.
Outgoing edges
applies_to1
- domain:ml-ai·DomainML/AI
covers1
- skill-area:general-knowledge-reasoning·SkillAreaGeneral Knowledge Reasoning
Incoming edges
None.