| Qwen3.5-Omni Technical Report | | 84.6 | Qwen3.5-Omni-Plus | 2026-04-21 |
| OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention | | 82.8 | OmniVideo-R1 (Qwen3-Omni-30B-A3B) | 2026-02-05 |
| OmniAgent: Audio-Guided Active Perception Agent for Omnimodal Audio-Video Understanding | ✓ Link | 82.71 | OmniAgent | 2025-12-29 |
| LongCat-Flash-Omni Technical Report | ✓ Link | 82.38 | LongCat-Flash-Omni Instruct | 2025-10-31 |
| Realtime-Venus: A full-duplex interaction system with asynchronous delegation | | 81.3 | Realtime-Venus-Omni | 2026-09-12 |
| TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming | ✓ Link | 80.5 | TLive-Omni-9B | 2026-08-21 |
| MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction | ✓ Link | 80.2 | MiniCPM-o 4.5-Instruct | 2026-04-30 |
| OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning | | 80.0 | OmniSeek (ours) | 2026-10-01 |
| Omni Interaction Agent Technical Report | ✓ Link | 78.53 | Gander | 2026-09-08 |
| Qwen3-Omni Technical Report | ✓ Link | 75.8 | Qwen3-Omni-30B-A3B-Thinking | 2025-09-22 |
| Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence | ✓ Link | 74.5 | Nemotron 3 Nano Omni | 2026-04-27 |
| CogniRoute: Learning to Route Social Evidence in Omni-Modal Models | | 74.3 | CogniRoute | 2026-06-18 |
| Omni-Streaming Thinking | ✓ Link | 74.2 | OST | 2026-09-14 |
| Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos | | 73.9 | AVF-Think | 2026-07-17 |
| ChronusOmni: Improving Time Awareness of Omni-Modal Large Language Models | | 72.3 | ChronusOmni | 2026-09-08 |
| OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering | ✓ Link | 71.09 | OmniJigsaw (CMM) | 2026-04-09 |
| OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning | ✓ Link | 68.4 | OmniCaptioner-IF-7B | 2026-06-07 |
| When Vision Speaks for Sound | ✓ Link | 67.9 | Qwen3-Omni-30B + Thud | 2026-05-13 |
| LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning | ✓ Link | 67.4 | LatentOmni | 2026-05-21 |
| OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM | ✓ Link | 66.50 | OmniVinci | 2025-10-17 |
| FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs | ✓ Link | 65.8 | video-SALMONN 2 (7B) +OFF | 2026-01-20 |
| Native Active Perception as Reasoning for Omni-Modal Understanding | ✓ Link | 64.8 | OmniAgent-RL-7B | 2026-06-17 |
| Daily-Omni Leaderboard | ✓ Link | 62.07 | Qwen2.5-Omni-7B-Instruct | 2025-03-26 |
| Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities | | 61.82 | Daily-Omni-Baseline-Qwen2.5 | 2026-03-10 |
| Daily-Omni Leaderboard | ✓ Link | 60.23 | Qwen2.5-Omni-3B-Instruct | 2025-03-26 |
| HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context | ✓ Link | 58.47 | HumanOmniV2-7B | 2025-06-26 |
| Daily-Omni Leaderboard | ✓ Link | 50.71 | Ola 7B | 2025-02-06 |
| Daily-Omni Leaderboard | ✓ Link | 35.17 | VideoLLaMA2 7B | 2024-06-11 |
| Daily-Omni Leaderboard | ✓ Link | 28.32 | Unified-IO 2 XL | 2023-12-28 |
| Daily-Omni Leaderboard | ✓ Link | 28.24 | Unified-IO 2 XXL | 2023-12-28 |
| Daily-Omni Leaderboard | ✓ Link | 27.40 | Unified-IO 2 L | 2023-12-28 |