한국어EN
Evaluation & BenchmarksLMSYS

LMSYS launches Chatbot Arena

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Chatbot Arena launched — anonymous, randomized head-to-head battles + Elo

Why it matters

Shifted the focus from benchmarks with correct answers to evaluation based on human preference

Source — Primary sources first; secondary reports are labelled “Press”

Officiallmsys.orghttps://lmsys.org/blog/2023-05-03-arena/

Added in Week 35, 2026 · See that week

On the map — ⑯ Evaluation line

  1. Previous stopMMLU
  2. This recordChatbot Arena
  3. Next stopSWE-bench
See it on the map

Same week

Language Models Don't Always Say What They Think publishedPaperPlan-and-Solve Prompting publishedPaperProTeGi publishedPaperGeoffrey Hinton talks to MIT Technology Review right after leaving GooglePress

Nearby on the same axis

MT-Bench and LLM-as-a-judge publishedPaperHugging Face explains the MMLU score mismatch on the Open LLM LeaderboardOfficialSWE-bench releasedPaperStanford CRFM releases HELMPaper