SOTAVerified

Visual Question Answering

MLLM Leaderboard

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–200 of 2177 papers

TitleStatusHype
MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive DiversityCode2
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMsCode2
MM-REACT: Prompting ChatGPT for Multimodal Reasoning and ActionCode2
MiniGPT-Med: Large Language Model as a General Interface for Radiology DiagnosisCode2
Enhancing Large Vision Language Models with Self-Training on Image ComprehensionCode2
Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language ModelsCode2
MedM-VL: What Makes a Good Medical LVLM?Code2
Aligning Modalities in Vision Large Language Models via Preference Fine-tuningCode2
MedPromptX: Grounded Multimodal Prompting for Chest X-ray DiagnosisCode2
ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal ModelsCode2
GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist CollaborationCode2
Med-Flamingo: a Multimodal Medical Few-shot LearnerCode2
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision ModelsCode2
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-ExpertsCode2
Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration RateCode2
MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language UnderstandingCode2
MC-LLaVA: Multi-Concept Personalized Vision-Language ModelCode2
Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction TuningCode2
MDETR - Modulated Detection for End-to-End Multi-Modal UnderstandingCode2
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual ContextsCode2
CoLLaVO: Crayon Large Language and Vision mOdelCode2
MC-LLaVA: Multi-Concept Personalized Vision-Language ModelCode2
Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image AnalysisCode2
MG-LLaVA: Towards Multi-Granularity Visual Instruction TuningCode2
LOVA3: Learning to Visual Question Answering, Asking and AssessmentCode2
LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language ModelsCode2
A Simple Aerial Detection Baseline of Multimodal Language ModelsCode2
LLMGA: Multimodal Large Language Model based Generation AssistantCode2
Doe-1: Closed-Loop Autonomous Driving with Large World ModelCode2
LLaVA-Plus: Learning to Use Tools for Creating Multimodal AgentsCode2
Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language ModelsCode2
Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question AnsweringCode2
LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal ModelsCode2
Efficient Large Multi-modal Models via Visual Context CompressionCode2
LinVT: Empower Your Image-level Large Language Model to Understand VideosCode2
Dual Diffusion for Unified Image Generation and UnderstandingCode2
LingoQA: Visual Question Answering for Autonomous DrivingCode2
Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer ModelsCode2
Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language ModelsCode2
Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal UnderstandingCode2
List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMsCode2
Keeping Yourself is Important in Downstream Tuning Multimodal Large Language ModelCode2
JourneyDB: A Benchmark for Generative Image UnderstandingCode2
Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-ImprovementCode2
Large Continual Instruction AssistantCode2
InstructBLIP: Towards General-purpose Vision-Language Models with Instruction TuningCode2
Are Language Models Puzzle Prodigies? Algorithmic Puzzles Unveil Serious Challenges in Multimodal ReasoningCode2
Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference OptimizationCode2
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual ScenariosCode2
VHM: Versatile and Honest Vision Language Model for Remote Sensing Image AnalysisCode2
Show:102550
← PrevPage 4 of 44Next →
All datasetsMM-VetViP-BenchVQA v2 test-devBenchLMMMMBenchV*benchVQA v2 valMSRVTT-QAVQA v2 test-stdMMHal-BenchMSVD-QAPlotQA-D1

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MMCTAgent (GPT-4 + GPT-4V)GPT-4 score74.24—Unverified
2Qwen2-VL-72BGPT-4 score74—Unverified
3InternVL2.5-78BGPT-4 score72.3—Unverified
4GPT-4o +text rationale +IoTGPT-4 score72.2—Unverified
5Lyra-ProGPT-4 score71.4—Unverified
6GLM-4V-PlusGPT-4 score71.1—Unverified
7Phantom-7BGPT-4 score70.8—Unverified
8InternVL2.5-38BGPT-4 score68.8—Unverified
9InternVL2-26B (SGP, token ratio 64%)GPT-4 score65.6—Unverified
10Baichuan-Omni (7B)GPT-4 score65.4—Unverified