Papers with Code · CC BY-SA 4.0

TVBench

아카이브 평가 28건 · 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
Seed1.5-VL thinking	Average Accuracy 63.6	Seed1.5-VL Technical Report 2025-05-11	연결 없음
PLM-8B	Average Accuracy 63.5	PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding 2025-04-17	코드 1
Seed1.5-VL	Average Accuracy 61.5	Seed1.5-VL Technical Report 2025-05-11	연결 없음
V-JEPA 2 ViT-g 8B	Average Accuracy 60.6	V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning 2025-06-11	코드 1
PLM-3B	Average Accuracy 58.9	PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding 2025-04-17	코드 1
RRPO	Average Accuracy 56.5	Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization 2025-04-16	연결 없음
Tarsier-34B	Average Accuracy 55.5	Tarsier: Recipes for Training and Evaluating Large Video Description Models 2024-06-30	코드 1
Tarsier2-7B	Average Accuracy 54.7	Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding 2025-01-14	코드 1
Qwen2-VL-72B	Average Accuracy 52.7	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
IXC-2.5 7B	Average Accuracy 51.6	InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output 2024-07-03	코드 1
Aria	Average Accuracy 51.0	Aria: An Open Multimodal Native Mixture-of-Experts Model 2024-10-08	코드 1
PLM-1B	Average Accuracy 50.4	PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding 2025-04-17	코드 1
LLaVA-Video 72B	Average Accuracy 50.0	Video Instruction Tuning With Synthetic Data 2024-10-03	연결 없음
VideoLLaMA2 72B	Average Accuracy 48.4	VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs 2024-06-11	코드 1 · 코드 2 · 코드 3
Gemini 1.5 Pro	Average Accuracy 47.6	Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context 2024-03-08	코드 1
Tarsier-7B	Average Accuracy 46.9	Tarsier: Recipes for Training and Evaluating Large Video Description Models 2024-06-30	코드 1
LLaVA-Video 7B	Average Accuracy 45.6	Video Instruction Tuning With Synthetic Data 2024-10-03	연결 없음
Qwen2-VL-7B	Average Accuracy 43.8	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
VideoLLaMA2 7B	Average Accuracy 42.9	VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs 2024-06-11	코드 1 · 코드 2 · 코드 3
PLLaVA-34B	Average Accuracy 42.3	PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning 2024-04-25	코드 1
mPLUG-Owl3	Average Accuracy 42.2	mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models 2024-08-09	코드 1
VideoLLaMA2.1	Average Accuracy 42.1	VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs 2024-06-11	코드 1 · 코드 2 · 코드 3
VideoGPT+	Average Accuracy 41.7	VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding 2024-06-13	코드 1
GPT4o 8 frames	Average Accuracy 39.9	GPT-4o System Card 2024-10-25	연결 없음
PLLaVA-13B	Average Accuracy 36.4	PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning 2024-04-25	코드 1
ST-LLM	Average Accuracy 35.7	ST-LLM: Large Language Models Are Effective Temporal Learners 2024-03-30	코드 1
VideoChat2	Average Accuracy 35.0	MVBench: A Comprehensive Multi-modal Video Understanding Benchmark 2023-11-28	코드 1 · 코드 2 · 코드 3
PLLaVA-7B	Average Accuracy 34.9	PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning 2024-04-25	코드 1