AI Paper Atlas

Research map / Benchmarks / VQA-RAD

VQA-RAD leaderboard

22 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VQA-RAD. Best accuracy: 87.1 (PulseMind-72B, AAAI 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

VQA-RAD · accuracy

22 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
187.1PulseMind-72B
Qwen2.5-VL-72B
PulseMind: A Multi-Modal Medical Model for Real-World Clinical Diagnosis
AAAI 2026 · Table 1
Cross-modal learning
279.3CARE-7B
Hulu-Med-7B
CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models
ECCV 2026 · Table 1
Reasoning and chain of thought
378.3PTUnifier
CLIP-ViT-B + RoBERTa-base
Towards Unifying Medical Vision-and-Language Pre-Training via Soft Prompts
ICCV 2023 · Table 1
Cross-modal learning
477.57MedVLSynther-7B
Qwen2.5-VL-7B-Instruct
Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs
ICLR 2026 · Table 5
Visual question answering
577.29VISTA-SFT iteration 3
Qwen2.5-VL-7B-Instruct
Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training
ICML 2026 · Table 1
Multimodal LLMs
675.6MedSynapse-V (w/ anatomical encoder)
Qwen3-VL-8B
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
ECCV 2026 · Table 1
Multimodal LLMs
774.4MedVR
Qwen2.5-VL-7B
MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning
ICLR 2026 · Table 1
Multimodal LLMs
873.9MMedAgent-RL w/ test-time scaling
Qwen2.5-VL-7B
MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning
ICLR 2026 · Table 1
LLM agents
973.6Ophiuchus-7B
Qwen2.5-VL-7B
Ophiuchus: Incentivizing Tool-augmented ''Think with Images'' for Joint Medical Segmentation, Understanding and Reasoning
ICML 2026 · Table 1
Multimodal LLMs
1072.1Vision-G1
Qwen2.5-VL-7B
Vision-G1: Towards General Reasoning Vision-Language Models via Reinforcement Learning
AAAI 2026 · Table 3
Multimodal LLMs
12 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.