Our new X account is live! Follow @wizwand_team for updates

Judge Agreement on MT-bench Second Turn

95Agreement

G4-Pair

Updated 4d ago

Evaluation Results

Method	Links
G4-Pair 2023.06		95	727
G4-P 2023.06		95	727
Human 2023.06		91	629
G4-S 2023.06		89	193
G4-P 2023.06		88	205
Author 2023.06		87	31
Author 2023.06		86	273
G4-Pair 2023.06		85	864
G4-P 2023.06		85	864
G4-P 2023.06		85	557
G4-S 2023.06		85	506
G4-Single 2023.06		84	776
G4-S 2023.06		84	776
Author 2023.06		84	54
Human 2023.06		83	877
Human 2023.06		82	474
Human 2023.06		82	474
G4-Pair 2023.06		70	1,161
G4-P 2023.06		70	1,161
G4-P 2023.06		68	812
Author 2023.06		68	413
Human 2023.06		67	707
Author 2023.06		67	49
Human 2023.06		67	707
G4-Pair 2023.06		66	1,325
G4-P 2023.06		66	341
G4-P 2023.06		66	1,325
G4-S 2023.06		65	331
Author 2023.06		63	87
G4-S 2023.06		61	783
G4-Single 2023.06		59	1,285
G4-S 2023.06		59	1,285