# Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction

arXiv: https://arxiv.org/abs/2605.17360 · HTML: https://mlsanity.com/paper/2605.17360/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 50 references that are in the map.
- First posted on arXiv 17 May 2026.

## Builds on (most cited first, 30 of 40)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [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)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [PandaGPT: One Model To Instruction-Follow Them All](https://mlsanity.com/paper/2305.16355/) (2023)
- [Perception Test: A Diagnostic Benchmark for Multimodal Video Models](https://mlsanity.com/paper/2305.13786/) (2023)
- [VideoLLM-online: Online Video Large Language Model for Streaming Video](https://mlsanity.com/paper/2406.11816/) (2024)
- [CogVLM2: Visual Language Models for Image and Video Understanding](https://mlsanity.com/paper/2408.16500/) (2024)
- [OneLLM: One Framework to Align All Modalities with Language](https://mlsanity.com/paper/2312.03700/) (2023)
- [VITA: Towards Open-Source Interactive Omni Multimodal LLM](https://mlsanity.com/paper/2408.05211/) (2024)
- [VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset](https://mlsanity.com/paper/2305.18500/) (2023)
- [Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2406.08085/) (2024)
- [WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs](https://mlsanity.com/paper/2502.04326/) (2025)
- [StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding](https://mlsanity.com/paper/2411.03628/) (2024)
- [OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?](https://mlsanity.com/paper/2501.05510/) (2025)
- [OmniBench: Towards The Future of Universal Omni-Language Models](https://mlsanity.com/paper/2409.15272/) (2024)
- [Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities](https://mlsanity.com/paper/2503.04721/) (2025)
- [StreamingVLM: Real-Time Understanding for Infinite Video Streams](https://mlsanity.com/paper/2510.09608/) (2025)
- [Flash-VStream: Efficient Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2506.23825/) (2025)
- [StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant](https://mlsanity.com/paper/2505.05467/) (2025)
- [OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts](https://mlsanity.com/paper/2503.22952/) (2025)
- [LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs](https://mlsanity.com/paper/2603.19217/) (2026)
- [MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2512.06810/) (2025)
- [RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video](https://mlsanity.com/paper/2505.02064/) (2025)

## Built on by (most cited first, 3 of 3)

- [MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents](https://mlsanity.com/paper/2609.24812/) (2026)
- [Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models](https://mlsanity.com/paper/2610.08125/) (2026)
- [OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning](https://mlsanity.com/paper/2610.12458/) (2026)

## Abstract (arXiv)

Real-time duplex interaction is essential for multimodal AI systems operating in real-world scenarios, where models must continuously process streaming inputs and respond at appropriate moments. However, most existing multimodal large language models (MLLMs) are evaluated in offline settings, where the entire video input is processed before any response is generated. While recent work has started to explore real-time duplex MLLMs, there is still no comprehensive benchmark or automatic evaluation method for this setting. To address this gap, we propose Omni-DuplexEval, a benchmark for systematically evaluating real-time duplex interaction. The benchmark consists of two complementary scenarios: (1) Real-Time Description, which evaluates the ability to generate continuous, time-aligned responses that track evolving multimodal inputs, and (2) Proactive Reminder, which evaluates the ability to identify salient events and respond at appropriate moments. Omni-DuplexEval contains 660 videos with fine-grained, human-annotated labels and precise temporal metadata, spanning 9 tasks grounded in real-world scenarios, where all questions are formulated as open-ended queries. We further introduce an automatic evaluation framework based on LLM-as-a-Judge, which enables systematic assessment by jointly evaluating response-content alignment and response timing through timestamp-aware and sequential reasoning, achieving strong alignment with human judgments. Experiments on state-of-the-art duplex MLLMs reveal substantial limitations. The best-performing model achieves only 39.6% overall, while scoring only 20.0% on Proactive Reminder. Our analysis identifies two key challenges: models struggle to balance timely responses with coherent, holistic content generation, and they often fail to determine both when to respond and what to produce. We hope our work facilitates further progress in MLLMs.