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

Multiple Choice Question Answering on MMLU ProX Health

76.56Accuracy (ZH)

MED-COREASONER

Updated 4d ago

Evaluation Results

Method	Links
MED-COREASONER 2026.01		76.56	77.87	76.85	77.72	77.43	78.6	78.31	75.98	77.42
GPT-5.2 2026.01		72.63	73.94	73.94	76.42	77	75.69	75.98	70.6	74.53
MED-COREASONER 2026.01		71.91	71.91	72.34	73.36	74.52	73.22	73.91	68.85	72.5
MED-COREASONER 2026.01		71.9	71.32	71.62	71.76	73.22	73.21	73.07	69.14	71.91
GPT-5.1 2026.01		71.32	70.45	70.45	71.32	72.78	72.63	74.24	67.89	71.39
RAG + CoT 2026.01		69.14	69.87	67.83	70.31	72.63	70.89	72.63	65.6	69.86
Self-Consistency 2026.01		68.08	68.51	66.96	70.12	71.18	71.72	71.97	62.39	68.87
GPT-4o 2026.01		67.39	67.39	65.94	69.14	69.72	70.6	71.47	61.86	67.94
CoT 2026.01		67.1	61.28	63.61	70.31	72.34	70.01	71.32	60.99	67.12
DeepSeek-3.2 2026.01		66.81	66.81	61.28	69	68.7	67.89	69	51.67	65.15
SoT 2026.01		65.21	64.63	62.45	67.69	68.85	68.27	69.72	56.19	65.37
MED-COREASONER 2026.01		64.92	62.15	59.39	65.65	66.38	67.83	68.41	39.01	61.72
Qwen3-30B 2026.01		61.86	56.91	54.15	61.72	61.72	64.48	63.32	27.22	56.42
Qwen2.5-72B 2026.01		59.39	56.48	54.15	59.83	61.86	61.51	60.26	30.13	55.45
Qwen2.5-32B 2026.01		58.22	54.73	48.33	59.1	58.66	60.41	58.95	26.76	53.15
Claude-3.5-haiku 2026.01		56.33	57.64	54.88	60.7	61.72	59.97	62.59	35.81	56.21
LLaMA3.1-70B 2026.01		51.09	48.33	47.45	59.53	60.84	60.26	60.84	44.25	54.07