# Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

arXiv: https://arxiv.org/abs/2604.05015 · HTML: https://mlsanity.com/paper/2604.05015/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 30 of its 32 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 30 of 30)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos](https://mlsanity.com/paper/2501.13826/) (2025)
- [VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction](https://mlsanity.com/paper/2501.01957/) (2025)
- [MMVU: Measuring Expert-Level Multi-Discipline Video Understanding](https://mlsanity.com/paper/2501.12380/) (2025)
- [MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency](https://mlsanity.com/paper/2502.09621/) (2025)
- [Kwai Keye-VL 1.5 Technical Report](https://mlsanity.com/paper/2509.01563/) (2025)
- [MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models](https://mlsanity.com/paper/2501.02955/) (2025)
- [Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning](https://mlsanity.com/paper/2506.13654/) (2025)
- [VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception](https://mlsanity.com/paper/2509.21100/) (2025)
- [VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning](https://mlsanity.com/paper/2504.07956/) (2025)
- [Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding](https://mlsanity.com/paper/2507.15028/) (2025)
- [VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?](https://mlsanity.com/paper/2505.23359/) (2025)
- [Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition](https://mlsanity.com/paper/2602.08439/) (2026)
- [Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2603.18118/) (2026)

## Built on by (most cited first, 30 of 55)

- [LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence](https://mlsanity.com/paper/2605.25979/) (2026)
- [JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence](https://mlsanity.com/paper/2606.14777/) (2026)
- [VISD: Enhancing Video Reasoning via Structured Self-Distillation](https://mlsanity.com/paper/2605.06094/) (2026)
- [VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding](https://mlsanity.com/paper/2607.14935/) (2026)
- [Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model](https://mlsanity.com/paper/2607.24904/) (2026)
- [OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains](https://mlsanity.com/paper/2606.14702/) (2026)
- [AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?](https://mlsanity.com/paper/2605.27705/) (2026)
- [OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs](https://mlsanity.com/paper/2606.03890/) (2026)
- [Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events](https://mlsanity.com/paper/2606.02522/) (2026)
- [Kwai Keye-VL-2.0 Technical Report](https://mlsanity.com/paper/2606.10651/) (2026)
- [InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning](https://mlsanity.com/paper/2606.12195/) (2026)
- [MOSS-VL Technical Report](https://mlsanity.com/paper/2608.15045/) (2026)
- [GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs](https://mlsanity.com/paper/2605.10762/) (2026)
- [OmniInteract: Benchmarking Real-World Streaming Interaction for Real-Time Omnimodal Assistants](https://mlsanity.com/paper/2605.26485/) (2026)
- [Harnessing Streaming Video in the Wild](https://mlsanity.com/paper/2606.08615/) (2026)
- [Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning](https://mlsanity.com/paper/2606.27828/) (2026)
- [Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs](https://mlsanity.com/paper/2608.20492/) (2026)
- [Learning from the Near Future: Temporal Self-Distillation for RLVR](https://mlsanity.com/paper/2604.20733/) (2026)
- [Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning](https://mlsanity.com/paper/2605.28192/) (2026)
- [Sandboxed Coding Agents are Competitive Omni-modal Task Solvers](https://mlsanity.com/paper/2606.00579/) (2026)
- [Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction](https://mlsanity.com/paper/2606.05769/) (2026)
- [LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs](https://mlsanity.com/paper/2605.17260/) (2026)
- [Stable Curves, Unstable Items: Item-Level Scaling Heterogeneity in Video LLMs](https://mlsanity.com/paper/2608.07014/) (2026)
- [Qwen3.8-Omni: Towards Native Omni-Modal Agents](https://mlsanity.com/paper/2609.25611/) (2026)
- [EasyVideoR1: Easier RL for Video Understanding](https://mlsanity.com/paper/2604.16893/) (2026)
- [TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos](https://mlsanity.com/paper/2605.07593/) (2026)
- [GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions](https://mlsanity.com/paper/2605.15764/) (2026)
- [VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding](https://mlsanity.com/paper/2605.22907/) (2026)
- [Benchmarking Visual State Tracking in Multimodal Video Understanding](https://mlsanity.com/paper/2606.03920/) (2026)
- [One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding](https://mlsanity.com/paper/2608.05707/) (2026)

## Abstract (arXiv)

With the rapid advancement of video understanding, existing benchmarks are becoming increasingly saturated, exposing a critical discrepancy between inflated leaderboard scores and real-world model capabilities. To address this widening gap, we introduce Video-MME-v2, a comprehensive benchmark designed to rigorously evaluate the robustness and faithfulness of video understanding. To systematically evaluate model capabilities, we design a progressive tri-level hierarchy that incrementally increases the complexity of video comprehension, ranging from multi-point visual information aggregation, to temporal dynamics modeling, and ultimately to complex multimodal reasoning. Besides, in contrast to conventional per-question accuracy, we propose a group-based non-linear evaluation strategy that enforces both consistency across related queries and coherence in multi-step reasoning. It penalizes fragmented or guess-based correctness and assigns credit only to answers supported by valid reasoning. To guarantee data quality, Video-MME-v2 is constructed through a rigorously controlled human annotation pipeline, involving 12 annotators and 50 independent reviewers. Backed by 3,300 human-hours and up to 5 rounds of quality assurance, Video-MME-v2 aims to serve as one of the most authoritative video benchmarks. Extensive experiments reveal a substantial gap between current best model Gemini-3-Pro and human experts, and uncover a clear hierarchical bottleneck where errors in visual information aggregation and temporal modeling propagate to limit high-level reasoning. We further find that thinking-based reasoning is highly dependent on textual cues, improving performance with subtitles but sometimes degrading it in purely visual settings. By exposing these limitations, Video-MME-v2 establishes a demanding new testbed for the development of next-generation video MLLMs.