OpenCodePapers

zero-shot-video-question-answer-on-egoschema-fullset

Video Question AnsweringZero-Shot Video Question Answer
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
Kimi-VL Technical Report✓ Link78.5Kimi-VL-A3B-Instruct2025-04-10
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution✓ Link77.9Qwen2-VL-72B2024-09-18
InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning✓ Link76.6InternVideo3-8B2026-06-10
Qwen2.5-VL Technical Report✓ Link76.2Qwen2.5-VL-72B2025-02-19
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context✓ Link72.2Gemini 1.5 Pro2024-03-08
Hello GPT-4o72.2GPT-4o2024-05-13
Introducing Gemini 2.0: our new AI model for the agentic era71.5Gemini 2.0 Flash Experimental2024-12-11
BIMBA: Selective-Scan Compression for Long-Range Video Question Answering✓ Link71.14BIMBA-LLaVA-Qwen2-7B2025-03-12
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders✓ Link70.2Penguin-VL 8B2026-03-06
LinVT: Empower Your Image-level Large Language Model to Understand Videos✓ Link69.5LinVT-Qwen2-VL(7B)2024-12-06
Progressive Video Condensation with MLLM Agent for Long-form Video Understanding69.3ProVCA2026-04-03
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding✓ Link68.8PLM-8B2025-04-17
Qwen2.5-Omni Technical Report✓ Link68.6Qwen2.5-Omni2025-03-26
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding✓ Link67.6LongVU (7B)2024-10-22
Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing✓ Link66.9NVILA-8B-HD-Video2026-03-12
Aria: An Open Multimodal Native Mixture-of-Experts Model✓ Link66.8Aria2024-10-08
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution✓ Link66.7Qwen2-VL-7B2024-09-18
Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension✓ Link66.7Video-RAG (Based on LLaVA-Video)2024-11-20
LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos✓ Link66.1LENS (Qwen2.5-VL 7B, 32 frames)2026-07-27
HiCrew: Hierarchical Reasoning for Long-Form Video Understanding via Question-Aware Multi-Agent Collaboration64.6HiCrew2026-04-23
CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management✓ Link64.29Qwen2.5-VL-7B (with CurveStream)2026-03-20
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs✓ Link63.9VideoLLaMA2 (72B)2024-06-11
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction✓ Link63.6TASKER (GPT-4o)2026-06-28
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding✓ Link63.3VideoLLaMA3 7B2025-01-22
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction✓ Link63.1TASKER (GPT-4)2026-06-28
MeToM: Metadata-Guided Token Merging for Efficient Video LLMs62.4LLaVA-OneVision-7B + MeToM2026-06-03
H2SVC: Head-aware Heterogeneous Streaming Video Cache for Online Video Understanding62.1LLaVA-OV-7B + H2SVC2026-09-08
LLaVA-OneVision: Easy Visual Task Transfer✓ Link62.0LLaVA-OneVision-72B2024-08-06
Perception Encoder: The best visual embeddings are not at the output of the network✓ Link62.0PE-Lang G2025-04-17
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding✓ Link62.0Molmo2-8B2026-01-15
Tarsier: Recipes for Training and Evaluating Large Video Description Models✓ Link61.7Tarsier (34B)2024-06-30
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models✓ Link61.7AOT (LLaVA-OneVision-7B)2026-03-02
S3-Prune: Stability-Aware Token Budgeting for Long-Form Video-Language Models61.11S3-prune (LLaVA-OV-7B, 25% vision-token retention)2026-09-08
VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos✓ Link61.1VideoTree (GPT4)2024-05-29
Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA✓ Link61.1LVNet2024-06-13
OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams✓ Link60.9OmniStream-7B2026-03-12
Accelerating Streaming Video Large Language Models via Hierarchical Token Compression✓ Link60.8ReKV with STC-Pruner2025-11-30
EarlyTom: Early Token Compression Completes Fast Video Understanding✓ Link60.6EarlyTom (LLaVA-OneVision-7B)2026-05-28
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding✓ Link60.29HERMES (LLaVA-OV-7B, 4K tokens)2026-01-21
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding✓ Link60.2InternVideo2-6B2024-03-22
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning✓ Link60.0VideoChat-T (7B)2024-10-25
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark✓ Link56.7VideoChat2_phi32023-11-28
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark✓ Link55.8VideoChat2_HD_mistral2023-11-28
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders✓ Link55.7Penguin-VL 2B2026-03-06
Flexible Frame Selection for Efficient Video Reasoning55.6OpenLLoVi (Gemma) + FFS (Ours; @16.8→[4,32])2025-06-11
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution✓ Link54.9Qwen2-VL-2B2024-09-18
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark✓ Link54.4VideoChat2_mistral2023-11-28
Vamos: Versatile Action Models for Video Understanding✓ Link53.6Vamos (GPT-4o)2023-11-22
TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering✓ Link53.3TraveLER2024-04-01
A Simple LLM Framework for Long-Range Video Question-Answering✓ Link50.3LLoVi (GPT-3.5)2023-12-28
Video ReCap: Recursive Captioning of Hour-Long Videos✓ Link50.23Video ReCap2024-02-20
Vamos: Versatile Action Models for Video Understanding✓ Link48.3Vamos (GPT-4)2023-11-22
Language Repository for Long Video Understanding✓ Link41.2LangRepo (12B)2024-03-21
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding✓ Link38.70TimeMamba2024-03-14
Understanding Long Videos with Multimodal Language Models✓ Link37.6MVU (13B)2024-03-25
Vamos: Versatile Action Models for Video Understanding✓ Link36.7Vamos (13B)2023-11-22
A Simple LLM Framework for Long-Range Video Question-Answering✓ Link33.5LLoVi (7B)2023-12-28
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding✓ Link33.0TimeChat (7B)2023-12-04
InternVideo: General Video Foundation Models via Generative and Discriminative Learning✓ Link32.1InternVideo2022-12-06
mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality✓ Link31.1mPLUG-Owl (7B)2023-04-27
Zero-Shot Video Question Answering via Frozen Bidirectional Language Models✓ Link26.9FrozenBiLM2022-06-16
Self-Chained Image-Language Model for Video Localization and Question Answering✓ Link22.7SeViLA (4B)2023-05-11
20.0Random