Medical Information Retrieval on R2MED (original queries) benchmark leaderboard · SOTA2 Research

Medical Information Retrieval on R2MED (original queries)

43.18Average (nDCG@10)ReasonEmbed-Qwen3-8B

Evaluation Results

Method	Links
ReasonEmbed-Qwen3-8B2025.10		43.18	54.01	66.33	67.64	20.93	27.96	51.38	33.76	23.43
ReasonEmbed-Llama-3.1-8B2025.10		42.76	53.52	64.37	63.82	20.4	29.67	51.86	34.55	23.88
ReasonEmbed-Qwen3-8B2025.10		42.36	51.65	65.17	65.89	20.67	27.98	51.71	33.79	22.01
ReasonEmbed-Llama-3.1-8B2025.10		41.98	53.04	63.24	63.89	22.2	29.43	51.9	32.9	19.2
ReasonEmbed-Qwen3-4B2025.10		41.16	52.45	64.28	62.58	20.83	26.21	48.03	32.5	22.38
ReasonEmbed-Qwen3-4B2025.10		39.94	49.5	62.59	60.26	20.43	24.75	49.27	30.4	22.32
RaDeR-gte-Qwen2-7B2025.10		35.19	36.02	53.58	50.32	15.41	20.31	49.94	34.31	21.83
Qwen3-Embedding-8B2025.10		34.22	21.37	50.15	46.65	18.91	27.06	48.76	37.29	23.6
gte-Qwen2-7B-instruct2025.10		32.56	33.18	45.53	49.91	13.41	17.1	48.19	32.13	21.07
DIVER-Retriever2025.10		32.23	39.27	51.68	50.81	13.94	16.1	38.56	24.69	22.81
Qwen3-Embedding-4B2025.10		31.75	18.16	47.73	43.37	17.25	22.9	47.19	33.65	23.76
NV-Embed-v22025.10		31.43	27.15	50.1	47.81	10.9	16.72	44.05	39.91	14.81
GritLM-7B2025.10		31.12	24.99	43.98	45.94	12.32	19.86	39.88	37.08	24.94
OpenAI-3-Large2025.10		28.57	23.82	40.51	44.05	11.78	15.01	47.43	28.87	17.12
ReasonIR-8B2025.10		27.94	26.16	44.84	39.28	11.21	14.92	36.56	29.2	21.37
Qwen3-8B-ms2025.10		24.15	17.02	38.11	39.33	5.37	9.51	31.85	30.88	21.11
Qwen3-4B-ms2025.10		23.09	16.05	37.3	33.67	5.28	8.79	31.55	29.63	22.43
Llama-3.1-8B-ms2025.10		22.34	13.17	34.76	34.3	5.64	8.83	33.1	30.68	18.23
BM252025.10		15.13	19.19	21.55	19.68	0.66	2.55	23.69	21.66	12.02