Share your thoughts, 1 month free Claude Pro on usSee more

Multiple-choice Question Answering on MMLU (test)

86.4Accuracy

GPT-4

Updated 23d ago

Evaluation Results

Method	Links
GPT-4 2023.03		86.4	-	-	-	-	-	-	-	-	-	-
Flan-PaLM 2023.03		75.2	-	-	-	-	-	-	-	-	-	-
U-PaLM 2023.03		70.7	-	-	-	-	-	-	-	-	-	-
GPT-3.5 2023.03		70	-	-	-	-	-	-	-	-	-	-
PPT (Distribution) 2026.05		65.5	-	-	-	-	-	-	-	-	-	-
Base 2026.05		65.1	-	-	-	-	-	-	-	-	-	-
PPT (Mean) 2026.05		64.9	-	-	-	-	-	-	-	-	-	-
PPT (Distribution) 2026.05		61.2	-	-	-	-	-	-	-	-	-	-
Base 2026.05		60	-	-	-	-	-	-	-	-	-	-
PPT (Mean) 2026.05		59.5	-	-	-	-	-	-	-	-	-	-
Verbalized 2026.05		42.8	-	-	-	-	-	-	-	-	-	-
BADS 2024.11		26.59	-	-	-	-	-	-	-	-	-	-
AMO 2026.05		26.24	-	-	-	-	-	-	-	-	-	-
Random_Select 2024.11		25.62	-	-	-	-	-	-	-	-	-	-
CDS 2024.11		25.62	-	-	-	-	-	-	-	-	-	-
AMO 2026.05		25.6	-	-	-	-	-	-	-	-	-	-
AskLLM-O 2024.11		25.55	-	-	-	-	-	-	-	-	-	-
Meta_Only 2024.11		25.51	-	-	-	-	-	-	-	-	-	-
Duplicate_Meta 2024.11		25.3	-	-	-	-	-	-	-	-	-	-
Mixing 2024.11		25.16	-	-	-	-	-	-	-	-	-	-
ClassAct 2024.11		24.9	-	-	-	-	-	-	-	-	-	-
Chinchilla 70B 2022.04		-	67.5	63.6	54.9	79.3	73.9	-	-	-	-	-
PaLM 8B 2022.04		-	25.3	25.6	23.8	24.1	27.8	-	-	-	-	-
PaLM 62B 2022.04		-	53.7	59.5	41.9	62.7	55.8	-	-	-	-	-
PaLM 540B 2022.04		-	69.3	77	55.6	81	69.6	-	-	-	-	-
Raw Conf 2026.06		-	-	-	-	-	-	17	0.9	0.71	0.54	0.72
HRE 2026.06		-	-	-	-	-	-	11	0.87	0.72	0.71	0.77
NWKR 2026.06		-	-	-	-	-	-	7	0.9	0.73	0.74	0.79
ACUTE 2026.06		-	-	-	-	-	-	7	0.91	0.73	0.74	0.79
ACUTE 2026.06		-	-	-	-	-	-	7	0.91	0.76	0.78	0.82
ACUTE 2026.06		-	-	-	-	-	-	7	0.91	0.77	0.8	0.83
ACUTE 2026.06		-	-	-	-	-	-	9	0.9	0.75	0.78	0.81
ACUTE 2026.06		-	-	-	-	-	-	8	0.91	0.76	0.78	0.82
ACUTE 2026.06		-	-	-	-	-	-	8	0.91	0.76	0.77	0.81