Papers with Code · CC BY-SA 4.0

MM-Vet

아카이브 평가 231건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
MoE-LLaVA-2.7B×4-Top2	GPT-4 score 35.9	MoE-LLaVA: Mixture of Experts for Large Vision-Language Models 2024-01-29	코드 1 · 코드 2 · 코드 3
SoM-LLaVA-1.5	GPT-4 score 35.9	List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs 2024-04-25	코드 1
Dragonfly (Llama3-8B)	GPT-4 score 35.9	Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models 2024-06-03	코드 1
Ferret-v2-13B	GPT-4 score 35.7	Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models 2024-04-11	코드 1
AlignGPT (Vicuna-13B)	GPT-4 score 35.6	AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability 2024-05-23	연결 없음
LLaVA-HR-X	GPT-4 score 35.5	Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models 2024-03-05	코드 1
SQ-LLaVA	GPT-4 score 35.5	SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant 2024-03-17	코드 1 · 코드 2
LOVA$^3$	GPT-4 score 35.2 Params 7B	LOVA3: Learning to Visual Question Answering, Asking and Assessment 2024-05-23	코드 1
LLaVA-InternLM2-7B-ViT + MoSLoRA	GPT-4 score 35.2	Mixture-of-Subspaces in Low-Rank Adaptation 2024-06-16	코드 1
InternLM2+ViT (QMoSLoRA)	GPT-4 score 35.2	Mixture-of-Subspaces in Low-Rank Adaptation 2024-06-16	코드 1
LLaVA1.5-7B-MDA	GPT-4 score 35.20 Params 7B	Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance 2024-11-21	연결 없음
Mipha-3B+	GPT-4 score 35.1	Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge 2024-07-05	연결 없음
LLaVA-Plus-13B (All Tools, V1.3, 336px)	GPT-4 score 35.0±0.0 Params 13B	LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents 2023-11-09	코드 1
Merlin	GPT-4 score 34.9	Merlin:Empowering Multimodal LLMs with Foresight Minds 2023-11-30	연결 없음
Arcana	GPT-4 score 34.8	Improving Multi-modal Large Language Model through Boosting Vision Capabilities 2024-10-17	연결 없음
INF-LLaVA	GPT-4 score 34.5	INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model 2024-07-23	코드 1
LLaVA-1.5+MMInstruct (Vicuna-7B)	GPT-4 score 34.4	MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity 2024-07-22	코드 1
Janus	GPT-4 score 34.3	Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation 2024-10-17	코드 1
LLaVA-TokenPacker (Vicuna-13B)	GPT-4 score 34.1	TokenPacker: Efficient Visual Projector for Multimodal LLM 2024-07-02	코드 1
γ-MoD-LLaVA-HR	GPT-4 score 34.0	$γ-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models 2024-10-17	연결 없음
LLaVA-1.5-7B (CSR)	GPT-4 score 33.9 Params 7B	Calibrated Self-Rewarding Vision Language Models 2024-05-23	코드 1
DynMOE-LLaVA	GPT-4 score 33.6	Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models 2024-05-23	코드 1
Imp-2B	GPT-4 score 33.5 Params 2B	Imp: Highly Capable Large Multimodal Models for Mobile Devices 2024-05-20	코드 1
InfMLLM-7B-Chat	GPT-4 score 33.4	InfMLLM: A Unified Framework for Visual-Language Tasks 2023-11-12	코드 1 · 코드 2
Video-LaVIT	GPT-4 score 33.2 Params 7B	Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization 2024-02-05	코드 1
LLaVA-Instruct (Vicuna-1.5-7B)	GPT-4 score 32.9	MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment 2024-06-28	코드 1 · 코드 2
VisionZip (Retain 128 Tokens, fine-tuning)	GPT-4 score 32.9	VisionZip: Longer is Better but Not Necessary in Vision Language Models 2024-12-05	코드 1
Uni-MoE	GPT-4 score 32.8	Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts 2024-05-18	코드 1
VL-Mamba (Mamba LLM-2.8B)	GPT-4 score 32.6	VL-Mamba: Exploring State Space Models for Multimodal Learning 2024-03-20	연결 없음
LLaVA-v1.5 (7B, w/ STIC)	GPT-4 score 32.6 Params 7B	Enhancing Large Vision Language Models with Self-Training on Image Comprehension 2024-05-30	코드 1