OpenCodePapers

zero-shot-video-question-answer-on-video-mme-w-o-subs

Video Question AnsweringZero-Shot Video Question Answer
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracy (%)ModelNameReleaseDate
Qwen3.5: Towards Native Multimodal Agents✓ Link83.9Qwen3.5-122B-A10B2026-02-16
Qwen3.5: Towards Native Multimodal Agents✓ Link83.7Qwen3.5-397B-A17B2026-02-16
Qwen3.5: Towards Native Multimodal Agents✓ Link82.8Qwen3.5-27B2026-02-16
Qwen3.5: Towards Native Multimodal Agents✓ Link82.5Qwen3.5-35B-A3B2026-02-16
Qwen3.5-Omni Technical Report81.9Qwen3.5-Omni-Plus2026-04-21
VideoJev: System One Model for Video Understanding and Interaction✓ Link81.8VideoJev-35B-A3B2026-10-13
Qwen3-VL Technical Report✓ Link79.2Qwen3-VL-235B-A22B-Instruct2025-11-26
Qwen3.5: Towards Native Multimodal Agents✓ Link78.4Qwen3.5-9B2026-02-16
Kwai Keye-VL-2.0 Technical Report✓ Link78.3Keye-VL-2.0-30B-A3B2026-06-09
Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension✓ Link77.4Video-RAG (based on LLaVA-Video)2024-11-20
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs✓ Link76.7Video-ORA-9B2026-08-20
TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming✓ Link75.6TLive-Omni (9B)2026-08-21
VideoJev: System One Model for Video Understanding and Interaction✓ Link75.0VideoJev-4B2026-10-13
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning✓ Link74.8GLM-4.6V2025-07-01
Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence74.19Capek0.5-35B-A3B2026-08-07
InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning✓ Link73.8InternVideo3-8B2026-06-10
Qwen2.5-VL Technical Report✓ Link73.3Qwen2.5-VL-72B2025-02-19
Kwai Keye-VL 1.5 Technical Report✓ Link73.0Keye-VL-1.5-8B2025-09-01
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models✓ Link72.7InternVL3-78B2025-04-14
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence✓ Link72.2Nemotron 3 Nano Omni (Reasoning)2026-04-27
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context✓ Link71.9Gemini 1.5 Pro2024-03-08
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence✓ Link71.9LLaVA-OneVision-2-8B2026-05-25
Less from More: Reinforcing Sparse Video Reasoning from Dense References✓ Link71.8SAVER-4B (extra data)2026-10-07
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice✓ Link71.7VideoAuto-R1 (Qwen3-VL-8B)2026-01-08
Qwen3-Omni Technical Report✓ Link71.4Qwen3-Omni-Flash-Instruct2025-09-22
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders✓ Link71.4Penguin-VL (8B)2026-03-06
TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming✓ Link71.3TLive-Omni (4B)2026-08-21
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution✓ Link71.2Qwen2-VL-72B2024-09-18
Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos70.7AVF-Instruct2026-07-17
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction✓ Link70.4MiniCPM-o 4.5-Instruct2026-04-30
Enhancing Video Vision Language Model with Hippocampal Sensing70.4HippoVLM-8B2026-06-03
GPT-4o: Visual perception performance of multimodal large language models in piglet activity understanding70.3GPT-4o2024-06-14
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding✓ Link70.1VideoChat3-4B2026-07-16
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding✓ Link69.9Molmo2-8B2026-01-15
PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models✓ Link68.22PhysBrain 1.5-8B2026-09-14
MOSS-VL Technical Report✓ Link68.1MOSS-VL-Instruct-07082026-08-15
Kimi-VL Technical Report✓ Link67.8Kimi-VL-A3B-Instruct2025-04-10
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models67.8Insight-V++ (Self-Evolving, Qwen2.5-VL, 7B)2026-03-18
Small Vision-Language Models are Smart Compressors for Long Video Understanding✓ Link67.8Tempo2026-04-09
Kwai Keye-VL Technical Report✓ Link67.7Keye-VL-8B2025-07-02
From Pixels to Words -- Towards Native One-Vision Models at Scale✓ Link67.4NEO-ov 9B2026-05-27
VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context✓ Link67.4VisReflect-7B-Video2026-06-29
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context✓ Link66.3Gemini 1.5 Flash2024-03-08
LLaVA-OneVision: Easy Visual Task Transfer✓ Link66.2LLaVA-OneVision-72B2024-08-06
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding✓ Link66.2VideoLLaMA3 7B2025-01-22
Reinforced Attention Learning65.1RAL-zero2026-02-04
AURA: Always-On Understanding and Real-Time Assistance via Video Streams✓ Link65.1AURA (8B)2026-04-05
64.8LLaVA-OneVision (72B)
Structured Causal Video Reasoning via Multi-Objective Alignment64.7STEER-4B2026-04-06
Watch Before You Answer: Learning from Visually Grounded Post-Training✓ Link63.4VidGround (64 frames)2026-04-06
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution✓ Link63.3Qwen2-VL-7B2024-09-18
VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting✓ Link63.3VisionCoach-7B2026-03-15
PointThinker: Point-Incentivized Parallel Thinking for Multimodal Large Language Model62.5PointThinker-7B (extra data)2026-06-03
FlexiVideo: Variation-Aware Temporal Dynamics Modeling for Efficient Video Understanding✓ Link62.5FlexiVideo-3B (extra data)2026-06-03
GPT-4o: Visual perception performance of multimodal large language models in piglet activity understanding62.3GPT-4o mini2024-06-14
Incentivizing Versatile Video Reasoning in MLLMs via Data-Efficient Reinforcement Learning✓ Link62.0VideoReasoner2026-06-03
VILA: On Pre-training for Visual Language Models✓ Link61.4VILA-1.5 (34B)2023-12-12
Dynin-Omni: Omnimodal Unified Large Diffusion Language Model✓ Link61.4Dynin-Omni (8B)2026-03-09
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs✓ Link60.9VideoLLaMA2 (72B)2024-06-11
OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams✓ Link60.7OmniStream-7B2026-03-12
EVA: Efficient Reinforcement Learning for End-to-End Video Agent✓ Link59.9EVA (GRPO)2026-03-24
TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding✓ Link58.8TimeViper2025-11-20
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation✓ Link57.33PixelUMM 8B MoT2026-09-29
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution✓ Link55.6Qwen2-VL-2B2024-09-18
Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction54.4GAS (4B)2026-08-12
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding✓ Link53.0MoE-ViE-H/14 + Llama 3.1 8B (42M alignment)2026-08-18
SmolVLM: Redefining small and efficient multimodal models✓ Link52.1SmolVLM 2.2B2025-04-07
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning✓ Link46.3VideoChat-T (7B)2024-10-25