List your company
ResearchFormerly WizWand

Multi-Modal Visual Question Answering on CT-RATE (val)

41.92AccuracyMed3D-R1
20.776826.265931.75537.2441Feb 1, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Med3D-R1Input Type=Volume, LLM Backbone=Qwen-2.5-3B, Training Stage=S2, Reasoning Instruction=w think2026.0241.92
Med3D-R1Input Type=Volume, LLM Backbone=Qwen-2.5-3B, Training Stage=S2, Reasoning Instruction=w/o think2026.0240.3
Qwen3-VL-4B-InstructInput Type=Montage, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w/o think2026.0233.52
Qwen3-VL-4B-ThinkingInput Type=Montage, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w/o think2026.0232.77
Lingshu-7BInput Type=Montage, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w/o think2026.0231.88
Qwen2.5-VL-3B-RLInput Type=Video, LLM Backbone=Qwen-2.5-3B, Reasoning Instruction=w think2026.0231.22
Qwen3-VL-4B-InstructInput Type=Montage, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w think2026.0229.93
Qwen2.5-VL-3BInput Type=Montage, LLM Backbone=Qwen-2.5-3B, Reasoning Instruction=w think2026.0229.5
Med-R1Input Type=Montage, LLM Backbone=Qwen-2-2B, Reasoning Instruction=w think2026.0229.32
Qwen2.5-VL-3BInput Type=Video, LLM Backbone=Qwen-2.5-3B, Reasoning Instruction=w think2026.0229.3
Qwen2.5-VL-7BInput Type=Montage, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w think2026.0229.23
Lingshu-7BInput Type=Video, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w/o think2026.0229.14
Qwen2.5-VL-7BInput Type=Montage, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w/o think2026.0228.98
Qwen3-VL-4B-ThinkingInput Type=Video, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w/o think2026.0228.95
Qwen2.5-VL-3B-RLInput Type=Video, LLM Backbone=Qwen-2.5-3B, Reasoning Instruction=w/o think2026.0228.73
Qwen3-VL-4B-InstructInput Type=Video, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w/o think2026.0228.65
Lingshu-7BInput Type=Montage, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w think2026.0228.54
Lingshu-7BInput Type=DRR, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w/o think2026.0228.14
Qwen3-VL-4B-ThinkingInput Type=Montage, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w think2026.0228
Med-R1Input Type=Montage, LLM Backbone=Qwen-2-2B, Reasoning Instruction=w/o think2026.0227.96
Qwen3-VL-4B-InstructInput Type=DRR, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w/o think2026.0227.86
Med-R1Input Type=DRR, LLM Backbone=Qwen-2-2B, Reasoning Instruction=w/o think2026.0227.36
Qwen2.5-VL-3BInput Type=Video, LLM Backbone=Qwen-2.5-3B, Reasoning Instruction=w/o think2026.0227.36
Qwen2.5-VL-3BInput Type=Montage, LLM Backbone=Qwen-2.5-3B, Reasoning Instruction=w/o think2026.0227.35
Med3D-R1Input Type=Volume, LLM Backbone=Qwen-2.5-3B, Training Stage=S1, Reasoning Instruction=w/o think2026.0227.32
Med3D-R1Input Type=Volume, LLM Backbone=Qwen-2.5-3B, Training Stage=S1, Reasoning Instruction=w think2026.0227.12
MedGemma-4BInput Type=DRR, LLM Backbone=Gemma-3-4B, Reasoning Instruction=w/o think2026.0227.1
Qwen2.5-VL-7BInput Type=Video, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w think2026.0226.89
Med-R1Input Type=DRR, LLM Backbone=Qwen-2-2B, Reasoning Instruction=w think2026.0226.86
MedGemma-4BInput Type=DRR, LLM Backbone=Gemma-3-4B, Reasoning Instruction=w think2026.0226.76
Qwen2.5-VL-7BInput Type=Video, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w/o think2026.0226.63
MedVLM-R1Input Type=Montage, LLM Backbone=Qwen-2-2B, Reasoning Instruction=w think2026.0226.58
Qwen3-VL-4B-ThinkingInput Type=DRR, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w/o think2026.0226.54
Qwen3-VL-4B-ThinkingInput Type=Video, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w think2026.0226.45
Qwen3-VL-4B-InstructInput Type=Video, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w think2026.0226.34
Lingshu-7BInput Type=DRR, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w think2026.0226.32
Lingshu-7BInput Type=Video, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w think2026.0226.17
MedVLM-R1Input Type=Montage, LLM Backbone=Qwen-2-2B, Reasoning Instruction=w/o think2026.0226.13
Qwen2.5-VL-7BInput Type=DRR, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w/o think2026.0225.85
Qwen3-VL-4B-InstructInput Type=DRR, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w think2026.0225.85
RadFMInput Type=Volume, LLM Backbone=Llama-2-13B, Reasoning Instruction=w/o think2026.0225.77
Qwen2.5-VL-3BInput Type=DRR, LLM Backbone=Qwen-2.5-3B, Reasoning Instruction=w think2026.0225.7
MedGemma-1.5-4BInput Type=DRR, LLM Backbone=Gemma-3-4B, Reasoning Instruction=w think2026.0225.53
E3D-GPTInput Type=Volume, LLM Backbone=Vicuna-1.5-7B, Reasoning Instruction=w/o think2026.0225.29
Qwen2.5-VL-7BInput Type=DRR, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w think2026.0225.01
MedVLM-R1Input Type=DRR, LLM Backbone=Qwen-2-2B, Reasoning Instruction=w think2026.0224.19
MedGemma-4BInput Type=Montage, LLM Backbone=Gemma-3-4B, Reasoning Instruction=w/o think2026.0224.06
MedGemma-4BInput Type=Montage, LLM Backbone=Gemma-3-4B, Reasoning Instruction=w think2026.0224
Qwen3-VL-4B-ThinkingInput Type=DRR, LLM Backbone=Qwen-3-4B, Reasoning Instruction=w think2026.0223.91
MedGemma-1.5-4BInput Type=DRR, LLM Backbone=Gemma-3-4B, Reasoning Instruction=w/o think2026.0223.35
CT-CHATInput Type=Volume, LLM Backbone=Llama-3.1-8B, Reasoning Instruction=w/o think2026.0223.14
Qwen2.5-VL-3BInput Type=DRR, LLM Backbone=Qwen-2.5-3B, Reasoning Instruction=w/o think2026.0223.09
MedGemma-1.5-4BInput Type=Montage, LLM Backbone=Gemma-3-4B, Reasoning Instruction=w think2026.0223.07
M3DInput Type=Volume, LLM Backbone=Llama-2-7B, Reasoning Instruction=w/o think2026.0222.68
MedVLM-R1Input Type=DRR, LLM Backbone=Qwen-2-2B, Reasoning Instruction=w/o think2026.0222.56
MedGemma-1.5-4BInput Type=Montage, LLM Backbone=Gemma-3-4B, Reasoning Instruction=w/o think2026.0221.71
Med3DVLMInput Type=Volume, LLM Backbone=Qwen-2.5-7B, Reasoning Instruction=w/o think2026.0221.59