List your company

Judge Agreement on Chatbot Arena Random = 33% (S1)

72Agreement RateGPT-4 (Pairwise)
52.2457.3762.567.63Jun 9, 2023

Evaluation results

MethodLinks
GPT-4 (Pairwise)Target Judge=GPT-4 (Single-answer)2023.06722,968
GPT-3.5 (Pairwise)Target Judge=Claude (Pairwise)2023.06683,057
GPT-4 (Pairwise)Target Judge=GPT-3.5 (Pairwise)2023.06663,061
GPT-4 (Pairwise)Target Judge=Claude (Pairwise)2023.06663,062
GPT-4 (Pairwise)Target Judge=Human2023.06643,066
GPT-4 (Single-answer)Target Judge=Claude (Pairwise)2023.06622,964
GPT-4 (Single-answer)Target Judge=GPT-3.5 (Pairwise)2023.06602,964
GPT-4 (Single-answer)Target Judge=Human2023.06602,968
GPT-3.5 (Pairwise)Target Judge=Human2023.06543,061
Claude (Pairwise)Target Judge=Human2023.06533,062