Papers with Code · CC BY-SA 4.0

NExT-QA

아카이브 평가 47건 · 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
LinVT-Qwen2-VL (7B)	Accuracy 85.5	LinVT: Empower Your Image-level Large Language Model to Understand Videos 2024-12-06	코드 1
InternVL-2.5(8B)	Accuracy 85.5	Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling 2024-12-06	코드 1
VideoLLaMA3(7B)	Accuracy 84.5	VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding 2025-01-22	코드 1
PLM-8B	Accuracy 84.1	PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding 2025-04-17	코드 1
BIMBA-LLaVA-Qwen2-7B	Accuracy 83.73	BIMBA: Selective-Scan Compression for Long-Range Video Question Answering 2025-03-12	코드 1
PLM-3B	Accuracy 83.4	PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding 2025-04-17	코드 1
LLaVA-Video	Accuracy 83.2	Video Instruction Tuning With Synthetic Data 2024-10-03	연결 없음
NVILA(8B)	Accuracy 82.2	NVILA: Efficient Frontier Visual Language Models 2024-12-05	코드 1 · 코드 2
Oryx-1.5(7B)	Accuracy 81.8	Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution 2024-09-19	코드 1
Qwen2-VL(7B)	Accuracy 81.2	Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution 2024-09-18	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8
LongVILA(7B)	Accuracy 80.7	LongVILA: Scaling Long-Context Visual Language Models for Long Videos 2024-08-19	코드 1
PLM-1B	Accuracy 80.3	PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding 2025-04-17	코드 1
LLaVA-OV(72B)	Accuracy 80.2	LLaVA-OneVision: Easy Visual Task Transfer 2024-08-06	코드 1 · 코드 2
VideoChat2_HD_mistral	Accuracy 79.5	MVBench: A Comprehensive Multi-modal Video Understanding Benchmark 2023-11-28	코드 1 · 코드 2 · 코드 3
LLaVA-OV(7B)	Accuracy 79.4	LLaVA-OneVision: Easy Visual Task Transfer 2024-08-06	코드 1 · 코드 2
LLaVA-NeXT-Interleave(14B)	Accuracy 79.1	LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models 2024-07-10	코드 1 · 코드 2 · 코드 3
VideoChat2_mistral	Accuracy 78.6	MVBench: A Comprehensive Multi-modal Video Understanding Benchmark 2023-11-28	코드 1 · 코드 2 · 코드 3
mPLUG-Owl3(8B)	Accuracy 78.6	mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models 2024-08-09	코드 1
LLaVA-NeXT-Interleave(7B)	Accuracy 78.2	LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models 2024-07-10	코드 1 · 코드 2 · 코드 3
LLaVA-NeXT-Interleave(DPO)	Accuracy 77.9	LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models 2024-07-10	코드 1 · 코드 2 · 코드 3
Vamos	Accuracy 77.3	Vamos: Versatile Action Models for Video Understanding 2023-11-22	코드 1
ViLA (3B)	Accuracy 75.6	ViLA: Efficient Video-Language Alignment for Video Question Answering 2023-12-13	코드 1
VideoLLaMA2.1(7B)	Accuracy 75.6	VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs 2024-06-11	코드 1 · 코드 2 · 코드 3
LLaMA-VQA (33B)	Accuracy 75.5	Large Language Models are Temporal and Causal Reasoners for Video Question Answering 2023-10-24	코드 1
ViLA (3B, 4 frames)	Accuracy 74.4	ViLA: Efficient Video-Language Alignment for Video Question Answering 2023-12-13	코드 1
CREMA	Accuracy 73.9	CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion 2024-02-08	코드 1
SeViLA	Accuracy 73.8	Self-Chained Image-Language Model for Video Localization and Question Answering 2023-05-11	코드 1
TCR	Accuracy 73.5	Text-Conditioned Resampler For Long Form Video Understanding 2023-12-19	연결 없음
LSTP	Accuracy 72.1	Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge 2024-02-25	코드 1 · 코드 2
Mirasol3B	Accuracy 72	Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities 2023-11-09	연결 없음