Visual Question Answering on PathMMU 1.0 (ALL test) benchmark leaderboard · SOTA2 Research

Visual Question Answering on PathMMU 1.0 (ALL test)

72.2Overall ScoreCPath-Omni

Evaluation Results

Method	Links
CPath-Omni2024.12		72.2	69.9	71.8	70.6	70.6	79
PathReasoner-R1-7B2026.01		63.91	66.17	64.69	65.78	72.88	50.03
Patho-R1-7B2026.01		63.37	66.06	67.93	66.43	75.34	45.4
PathGen-LLaVA2024.12		58.4	60.1	58.8	60.7	64.9	48.9
PathReasoner-SFT-7B2026.01		57.96	60.46	60.23	61.82	62.56	44.72
HuatuoGPT-Vision-7B2026.01		54.59	61.36	59.37	54.72	58.07	36.64
InternVL3.5-8B2026.01		50.38	54.04	53.32	50.8	54.07	39.09
GPT-4V-11062024.12		49.8	53.5	53.9	53.6	52.8	33.8
Qwen-VL-MAX2024.12		45.9	50.9	49.3	47.9	49.8	29.6
SlideChat-7B (Baseline)2026.01		45.65	49.3	46.88	47.12	52.4	32.55
MedVLThinker-7B2026.01		44.23	48.15	46.1	—	51.81	30.76
WSI-LLaVA-7B2026.01		43.82	48.3	45.7	45	49.5	29.8
Gemini Pro Vision2024.12		42.7	44.9	42	43.7	49.4	34.7
Quilt-LLaVA2024.12		41.5	42.6	46.6	45.3	42.7	29.2
Qwen3-VL-8B-Thinking2026.01		38.67	42.77	39.67	43.2	41.18	24.82
LLaVA-1.5-13B2024.12		37.6	41	40.4	39.4	44.3	23.5
InstructBLIP-FLAN-T5-XXL2024.12		33.9	37.2	34.3	36	39.3	22.7
Quilt-LLaVA-7B2026.01		32.02	34.8	35.29	36.72	41.43	14.71
LLaVA-Med2024.12		26.2	27.7	27.3	27.2	30.7	20.3
MedGemma-4B-IT2026.01		24.94	26.75	29.6	26.9	37.5	7.56
LLaVA-Med-7B2026.01		23.4	27.77	21.25	21.27	21.65	12.01
Qwen3-VL-8B-Instruct2026.01		18.59	21.31	20.54	21.51	21.4	7.72