Share your thoughts, 1 month free Claude Pro on usSee more

Medical Vision-Language Modeling on CT-FlowBench

58QA Score

Hulu-Med-7B

Updated 1mo ago

Evaluation Results

Method	Links
Hulu-Med-7B 2026.02		58	46	37	47
Gemini-3-Pro-Preview 2026.02		45	43	44	44
Claude-Sonnet-4.5 2026.02		44	44	43	43.67
CT-Flow-7B 2026.02		43	52	38	44.33
CT-Flow-8B 2026.02		42	40	47	43
M3D-RAD 2026.02		39	34	35	36
GPT-5.2 2026.02		35	40	37	37.33
Qwen3-VL-235B-A22B-Instruct 2026.02		30	36	36	34
Qwen3-VL-8B-Instruct 2026.02		30	26	20	25.33
GLM4.6-V 2026.02		25	33	34	30.67
M3D-LaMed-Llama-2-7B 2026.02		17	17	17	17
Qwen2.5-VL-7B-Instruct 2026.02		14	22	21	19