OpenCodePapers
medical-visual-question-answering-on-pathvqa
Visual Question Answering (VQA)
Medical Visual Question Answering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
Closed-Ended Accuracy
↕
ModelName
ReleaseDate
↕
LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding
✓ Link
95.15
LLaDA-MedV (extra data)
2025-08-03
K-PathVQA: Knowledge-Aware Multimodal Representation for Pathology Visual Question Answering
94.6
K-PathVQA (extra data)
2023-07-11
MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine
✓ Link
92.7
LLaVA-Tri with MedTrinity (extra data)
2024-08-06
Biomedical Visual Instruction Tuning with Clinician Preference Alignment
92.42
BioMed-VITAL (13B, 150K) (extra data)
2024-06-19
Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models
✓ Link
91.98
Med-MoE (Phi-2) (extra data)
2024-04-16
Dual-Level Confidence based Implicit Self-Refinement for Medical Visual Question Answering
✓ Link
89.84
DuCoR (Llama2)
2026-06-03
Q2ATransformer: Improving Medical VQA via an Answer Querying Decoder
88.85
Q2ATransformer
2023-04-04
Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models
87.0
GPT-2 + LoRA (extra data)
2023-03-10
Sparse Spectral LoRA: Routed Experts for Medical VLMs
✓ Link
84.2
MedQwen (extra data)
2026-04-01
Multiple Meta-model Quantifying for Medical Visual Question Answering
84.0
MMQ (BAN)
2021-05-19
PathVQA: 30000+ Questions for Medical Visual Question Answering
✓ Link
68.2
BAN + Faster R-CNN
2020-03-07
MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA
✓ Link
66.94
MedFG-VQA
2026-06-03
×