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
VisionZip (Retain 192 Tokens, fine-tuning)	GPT-4 score 32.6	VisionZip: Longer is Better but Not Necessary in Vision Language Models 2024-12-05	코드 1
VisionZip (Retain 128 Tokens)	GPT-4 score 32.6	VisionZip: Longer is Better but Not Necessary in Vision Language Models 2024-12-05	코드 1
LLaVA-v1.5 (+MoCa)	GPT-4 score 32.2	Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate 2024-10-09	코드 1
Dynamic-LLaVA-7B	GPT-4 score 32.2	Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification 2024-12-01	코드 1
Mipha-3B	GPT-4 score 32.1 Params 3B	Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models 2024-03-10	코드 1
VOLCANO 7B	GPT-4 score 32.0 Params 7B	Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision 2023-11-13	코드 1
Video-LLaVA	GPT-4 score 32.0	Video-LLaVA: Learning United Visual Representation by Alignment Before Projection 2023-11-16	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
TinyLLaVA-share-Sig-Ph	GPT-4 score 32.0 Params 3.1B	TinyLLaVA: A Framework of Small-scale Large Multimodal Models 2024-02-22	코드 1 · 코드 2
LLaVA-VT (Vicuna-7B)	GPT-4 score 31.8	Beyond Embeddings: The Promise of Visual Table in Visual Reasoning 2024-03-27	코드 1
LRV-Instruction-7B	GPT-4 score 31.7±0.1 Params 7B	Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning 2023-06-26	코드 1 · 코드 2 · 코드 3 · 코드 4
VisionZip (Retain 192 Tokens)	GPT-4 score 31.7	VisionZip: Longer is Better but Not Necessary in Vision Language Models 2024-12-05	코드 1
VisionZip (Retain 64 Tokens)	GPT-4 score 31.7	VisionZip: Longer is Better but Not Necessary in Vision Language Models 2024-12-05	코드 1
LLaVA-1.5-7B (+ SIMA)	GPT-4 score 31.6 Params 7B	Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement 2024-05-24	코드 1 · 코드 2
LLaMA-Adapter v2-7B	GPT-4 score 31.4±0.1 Params 7B	LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model 2023-04-28	코드 1 · 코드 2 · 코드 3
MiCo-Chat-7B	GPT-4 score 31.4	Explore the Limits of Omni-modal Pretraining at Scale 2024-06-13	코드 1
LLaVA-1.5-7B + TeamLoRA	GPT-4 score 31.2	TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition 2024-08-19	코드 1
LLaVA-1.5-7B	GPT-4 score 31.1±0.2 Params 7B	Improved Baselines with Visual Instruction Tuning 2023-10-05	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9
RoboCodeX-13B	GPT-4 score 31.0	RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis 2024-02-25	연결 없음
HyperLLaVA	GPT-4 score 31.0	HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models 2024-03-20	코드 1
FAST (Vicuna-7B)	GPT-4 score 31.0	Visual Agents as Fast and Slow Thinkers 2024-08-16	코드 1
JanusFlow	GPT-4 score 30.9	JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation 2024-11-12	코드 1
AlignGPT (Vicuna-7B)	GPT-4 score 30.8	AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability 2024-05-23	연결 없음
LLaVolta	GPT-4 score 30.7	Efficient Large Multi-modal Models via Visual Context Compression 2024-06-28	코드 1
LLaVA-AlignedVQ	GPT-4 score 30.7	Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Models 2024-11-08	연결 없음
LLaVA-1.5-HACL	GPT-4 score 30.4 Params 7.3B	Hallucination Augmented Contrastive Learning for Multimodal Large Language Model 2023-12-12	코드 1
MaVEn	GPT-4 score 30.4 Params 7.2B	MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model 2024-08-22	연결 없음
VisionZip (Retain 64 Tokens, fine-tuning)	GPT-4 score 30.2	VisionZip: Longer is Better but Not Necessary in Vision Language Models 2024-12-05	코드 1
H2OVL-Mississippi-0.8B	GPT-4 score 30.0	H2OVL-Mississippi Vision Language Models Technical Report 2024-10-17	연결 없음
RoboMamba	GPT-4 score 29.7	RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation 2024-06-06	연결 없음
LLaVA-TokenPacker (Vicuna-7B)	GPT-4 score 29.6	TokenPacker: Efficient Visual Projector for Multimodal LLM 2024-07-02	코드 1