| Qwen3.5-Omni Technical Report | | 62.8 | Qwen3.5-Omni-Plus | 2026-04-21 |
| OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning | | 62.4 | OmniSeek (ours) | 2026-10-01 |
| OmniAgent: Audio-Guided Active Perception Agent for Omnimodal Audio-Video Understanding | ✓ Link | 61.2 | OmniAgent | 2025-12-29 |
| LongCat-Flash-Omni Technical Report | ✓ Link | 60.89 | LongCat-Flash-Omni Instruct | 2025-10-31 |
| Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents | | 58.32 | Omni-Decision | 2026-09-24 |
| MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction | ✓ Link | 55.7 | MiniCPM-o 4.5-Instruct | 2026-04-30 |
| Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence | ✓ Link | 55.4 | Nemotron 3 Nano Omni (Reasoning) | 2026-04-27 |
| Qwen3-Omni Technical Report | ✓ Link | 54.0 | Qwen3-Omni-30B-A3B-Instruct | 2025-09-22 |
| Realtime-Venus: A full-duplex interaction system with asynchronous delegation | | 54 | Realtime-Venus-Omni | 2026-09-12 |
| CogniRoute: Learning to Route Social Evidence in Omni-Modal Models | | 53.8 | CogniRoute | 2026-06-18 |
| Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos | | 51.6 | AVF-Think | 2026-07-17 |
| When Vision Speaks for Sound | ✓ Link | 50.3 | Qwen3-Omni-30B + Thud | 2026-05-13 |
| Omni Interaction Agent Technical Report | ✓ Link | 49.62 | Gander | 2026-09-08 |
| OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning | ✓ Link | 49.4 | OmniCaptioner-IF-7B | 2026-06-07 |
| LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning | ✓ Link | 48.9 | LatentOmni | 2026-05-21 |
| FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs | ✓ Link | 48.77 | video-SALMONN 2 (7B) +OFF | 2026-01-20 |
| OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM | ✓ Link | 48.23 | OmniVinci | 2025-10-17 |
| ChronusOmni: Improving Time Awareness of Omni-Modal Large Language Models | | 47.8 | ChronusOmni | 2026-09-08 |
| Native Active Perception as Reasoning for Omni-Modal Understanding | ✓ Link | 47.2 | OmniAgent-RL-7B | 2026-06-17 |
| HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context | ✓ Link | 47.1 | HumanOmniV2-7B | 2025-06-26 |
| Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence | ✓ Link | 46.3 | Open-o3-Video-v2-4B | 2026-10-13 |
| Omni-Modal LLMs Know More Than They Say | | 45.7 | OMNI-CATALYST (Qwen2.5-Omni-7B) | 2026-10-12 |
| Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data | ✓ Link | 44.7 | Uni-MoE-2.0-Omni | 2025-11-16 |
| VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting | ✓ Link | 43.8 | VisionCoach-7B | 2026-03-15 |
| MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models | ✓ Link | 25.6 | VideoLLaMA2-AV + MAD | 2026-01-29 |