Multiple Choice Question Answering on Global-MMLU Medical (Multilingual) benchmark leaderboard · SOTA2 Research

Multiple Choice Question Answering on Global-MMLU Medical (Multilingual)

89.1Accuracy (ZH)MED-COREASONER

Evaluation Results

Method	Links
MED-COREASONER2026.01		89.1	88.02	88.9	88.09	88.47	89.54	89.16	87.62	88.61
MED-COREASONER2026.01		85.85	83.39	86.58	85.45	86.17	86.57	85.31	82.19	85.19
MED-COREASONER2026.01		84.98	83.78	83.77	84.85	85.38	84.91	84.45	81.52	84.2
GPT-5.22026.01		84.39	86.25	83.65	85.18	86.25	85.98	85.78	81.86	84.92
Self-Consistency2026.01		83.77	82.79	81.61	83.32	84.29	84.24	82.62	77.31	82.49
GPT-5.12026.01		83.72	84.18	82.86	85.18	86.3	85.71	85.77	79.19	84.11
RAG + CoT2026.01		82.92	81.86	81.26	83.46	83.52	84.05	83.39	77.94	82.3
GPT-4o2026.01		82.39	82.66	81.45	82.59	83.26	83.39	82.46	76.08	81.79
SoT2026.01		81.59	80.53	78.34	81.53	82.46	82.59	81.73	74.55	80.42
CoT2026.01		81.06	75.42	77.74	81.93	84.25	83.32	81.93	74.42	80
DeepSeek-3.22026.01		81.06	80.33	77.54	81.59	83.19	83.59	81.33	68.11	79.59
MED-COREASONER2026.01		80.23	78.8	75.48	79.67	80.27	80.6	79.14	50.76	75.62
Qwen2.5-72B2026.01		79.34	77.81	72.96	76.61	79.93	80.07	78.6	50.9	74.52
Qwen3-30B2026.01		77.54	76.21	72.69	77.87	79.4	78.67	77.48	51.03	73.86
Qwen2.5-32B2026.01		77.21	73.95	68.17	75.68	76.68	76.61	75.08	51.76	71.89
LLaMA3.1-70B2026.01		73.02	72.36	67.38	76.08	77.94	78.54	78.14	65.58	73.63
Claude-3.5-haiku2026.01		64.78	66.32	64.25	72.55	72.73	75.8	72.58	56.65	68.21