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
VW-LMM	GPT-4 score 44.0	Multi-modal Auto-regressive Modeling via Visual Words 2024-03-12	코드 1
MoAI	GPT-4 score 43.7 Params 7B	MoAI: Mixture of All Intelligence for Large Language and Vision Models 2024-03-12	코드 1
MM1-3B-Chat	GPT-4 score 43.7	MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training 2024-03-14	연결 없음
MM1.5-3B-MoE	GPT-4 score 43.7	MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning 2024-09-30	연결 없음
Imp-3B	GPT-4 score 43.3 Params 3B	Imp: Highly Capable Large Multimodal Models for Mobile Devices 2024-05-20	코드 1
ShareGPT4V-13B	GPT-4 score 43.1 Params 13B	ShareGPT4V: Improving Large Multi-Modal Models with Better Captions 2023-11-21	코드 1
Mini-Gemini (+MoCa)	GPT-4 score 42.9	Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate 2024-10-09	코드 1
MM1.5-7B	GPT-4 score 42.2	MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning 2024-09-30	연결 없음
MM1-7B-Chat	GPT-4 score 42.1	MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training 2024-03-14	연결 없음
FlashSloth	GPT-4 score 41.9 Params 3.2B	FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression 2024-12-05	코드 1
DeepSeek-VL	GPT-4 score 41.5	DeepSeek-VL: Towards Real-World Vision-Language Understanding 2024-03-08	코드 1
LaVA1.5-13B-BPO	GPT-4 score 41.4 Params 13B	Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization 2024-03-13	연결 없음
ASMv2	GPT-4 score 41.3	The All-Seeing Project V2: Towards General Relation Comprehension of the Open World 2024-02-29	코드 1
FocusLLaVA	GPT-4 score 41.3	FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression 2024-11-21	연결 없음
SeVa-13B	GPT-4 score 41.0	Self-Supervised Visual Preference Alignment 2024-04-16	코드 1
MM1.5-3B	GPT-4 score 41.0	MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning 2024-09-30	연결 없음
LLaVA-1.5-7B (VG-S)	GPT-4 score 40.4	ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models 2024-12-09	코드 1
CoLLaVO	GPT-4 score 40.3 Params 7B	CoLLaVO: Crayon Large Language and Vision mOdel 2024-02-17	코드 1
SPHINX-2k	GPT-4 score 40.2	SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models 2023-11-13	코드 1
LLaVA-1.5 (LVIS-Instrcut4V)	GPT-4 score 40.2 Params 13B	To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning 2023-11-13	코드 1 · 코드 2
mPLUG-Owl3	GPT-4 score 40.1	mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models 2024-08-09	코드 1
Mono-InternVL-2B	GPT-4 score 40.1 Params 2B	Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training 2024-10-10	연결 없음
LLaVA1.5-13B-MDA	GPT-4 score 39.90 Params 13B	Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance 2024-11-21	연결 없음
LLaVA-VT (Vicuna-13B)	GPT-4 score 39.8	Beyond Embeddings: The Promise of Visual Table in Visual Reasoning 2024-03-27	코드 1
MM1.5-1B-MoE	GPT-4 score 39.8	MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning 2024-09-30	연결 없음
Janus-Pro-1B	GPT-4 score 39.8	Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling 2025-01-29	코드 1
SQ-LLaVA∗	GPT-4 score 39.7	SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant 2024-03-17	코드 1 · 코드 2
OmniFusion (grid split + ruDocVQA)	GPT-4 score 39.40	OmniFusion Technical Report 2024-04-09	연결 없음
DeepStack-L-HD (Vicuna-13B)	GPT-4 score 39.3	DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs 2024-06-06	연결 없음
LAF-13B	GPT-4 score 38.9	From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information 2024-01-31	연결 없음