List your company

Medical Vision-Language Modeling on CT-FlowBench

58QA ScoreHulu-Med-7B
12.2424.123647.88Feb 23, 2026

Evaluation results

MethodLinks
Hulu-Med-7BTool-use=false2026.0258463747
Gemini-3-Pro-PreviewTool-use=true2026.0245434444
Claude-Sonnet-4.5Tool-use=true2026.0244444343.67
CT-Flow-7BTool-use=true2026.0243523844.33
CT-Flow-8BTool-use=true2026.0242404743
M3D-RADTool-use=false2026.0239343536
GPT-5.2Tool-use=true2026.0235403737.33
Qwen3-VL-235B-A22B-InstructTool-use=true2026.0230363634
Qwen3-VL-8B-InstructTool-use=true2026.0230262025.33
GLM4.6-VTool-use=true2026.0225333430.67
M3D-LaMed-Llama-2-7BTool-use=false2026.0217171717
Qwen2.5-VL-7B-InstructTool-use=true2026.0214222119