AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models

Alejandro Lozano, Ryan D'Cunha, Daniel Jarquin, Min Sun, Josiah Aklilu, James Burgess, Yuhui Zhang, Paola Robayo, Jin Ye, Ming Hu, Zhongying Deng, Junjun He and 6 more

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the image input (vs text-only) (ablation)OctoMed-7B · MMBU closed VQAF1: 0.161 -> 0.361Improved
add the image input (vs text-only) (ablation)Qwen3-VL-32B · MMBU closed VQAF1: 0.211 -> 0.405Improved
add the image input (vs text-only) (ablation)MedGemma-1.5-4B · MMBU closed VQAF1: 0.201 -> 0.309Improved
add the image input (vs text-only) (ablation)Qwen3-VL-32B · MMBU open VQAF1: 0.016 -> 0.117Improved
add the image input (vs text-only) (ablation)OctoMed-7B · MMBU open VQAF1: 0.045 -> 0.048No clear effect
medical adaptation (MedGemma-4B vs Gemma-3-4B)Gemma-3-4B · MMBU ungrounded classification (closed)micro-F1: 0.296 -> 0.317Improved
medical adaptation (LLaVA-Med-7B vs LLaVA-v1.5-7B)LLaVA-v1.5-7B · MMBU ungrounded classification (closed)micro-F1: 0.254 -> 0.157Hurt
medical adaptation (MedGemma-1.5-4B vs Gemma-3-4B)Gemma-3-4B · MMBU grounded classification from detection (closed)micro-F1: 0.183 -> 0.204Improved
medical adaptation (Lingshu-32B vs Qwen2.5-VL-32B)Qwen2.5-VL-32B · MMBU domain radar areaarea: 1.03 -> 0.70Hurt
medical adaptation (OctoMed-7b vs Qwen2.5-VL-7b)Qwen2.5-VL-7B · MMBU domain radar areaarea: 0.43 -> 0.83Improved
scale model size 3B to 32BQwen2.5-VL · MMBU ungrounded classification (closed)micro-F1: 0.109 -> 0.320Improved
scale Lingshu from 7B to 32BLingshu · MMBU ungrounded classification (closed)micro-F1: 0.150 -> 0.333Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy