List your company

LLM Evaluation Agreement on MT-bench First Turn

97AgreementG4-Pair
58.5268.5178.588.49Jun 9, 2023

Evaluation results

MethodLinks
G4-PairSetup=S2 (R = 50%), Reference Judge=G4-Single2023.0697662
G4-PairSetup=S2 (R = 50%), Reference Judge=Human2023.0685859
G4-SingleSetup=S2 (R = 50%), Reference Judge=Human2023.0685739
HumanSetup=S2 (R = 50%), Reference Judge=Human2023.0681479
G4-PairSetup=S1 (R = 33%), Reference Judge=G4-Single2023.06701,138
G4-PairSetup=S1 (R = 33%), Reference Judge=Human2023.06661,343
HumanSetup=S1 (R = 33%), Reference Judge=Human2023.0663521
G4-SingleSetup=S1 (R = 33%), Reference Judge=Human2023.06601,280