Medical Reasoning on DeepTumorVQA refined 2025b benchmark leaderboard · SOTA2 Research

Medical Reasoning on DeepTumorVQA refined 2025b

0.77Fatty Liver Accuracy3DMedAgent (GPT-5)

Evaluation Results

Method	Links
3DMedAgent (GPT-5)2026.02		0.77	0.8	0.58	0.72	0.77	0.53	0.7
3DMedAgent (Qwen3-VL)2026.02		0.63	0.73	0.52	0.62	0.6	0.43	0.59
HuatuoGPT2026.02		0.35	0.47	0.47	0.18	0.47	0.2	0.36
Rand2026.02		0.33	0.5	0.5	0.33	0.5	0.25	0.4
GPT-52026.02		0.3	0.44	0.5	0.3	0.65	0.4	0.43
Qwen3-VL2026.02		0.3	0.63	0.58	0.18	0.65	0.37	0.45
MedGemma2026.02		0.3	0.43	0.53	0.23	0.47	0.13	0.35
RadFM2026.02		0.28	0.3	0.52	0.32	0.53	0.25	0.37
M3D2026.02		0.27	0.44	0.52	0.52	0.52	0.2	0.42