Unverified60% confidenceFactExact time
The LLM-as-judge approach was first adopted at scale in MT-Bench and Chatbot Arena.
2
Sources
60%
Confidence
Long-term
Relevance
8/5/2026
First Seen
Sources
Related Claims
UnverifiedCommon large model evaluation benchmarks include MMLU, HumanEval, MATH, MT-Bench, and LMSYS Arena.60% similarVerifiedLMARENA (formerly LMSYS Chatbot Arena) is a large model capability evaluation platform initiated by the University of California, Berkeley, using a human blind-test battle mechanism.50% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/691133API
curl https://kongchang.com/api/v1/knowledge/claims/691133MCP
get_claim(id=691133)