General & Complex QA on WSense
53Accuracy (All)Omni-o3
Evaluation results
| Method | Links | |
|---|---|---|
| Omni-o32026.04 | 53 | |
| Qwen3-OmniRelease Date=Sep 252026.04 | 48.3 | |
| Gemini1.5 ProRelease Date=Dec 242026.04 | 48 | |
| HumanOmniV2Release Date=June 252026.04 | 47.1 | |
| AVATARSource=CVPR 262026.04 | 46 | |
| EchoInk-R1Release Date=May 252026.04 | 45.7 | |
| Qwen2.5-OmniRelease Date=Mar 252026.04 | 45.4 | |
| AV-ReasonerRelease Date=June 252026.04 | 44.6 | |
| OlaRelease Date=Feb 252026.04 | 44.2 | |
| Omni-R1Release Date=May 252026.04 | 44.1 | |
| Qwen3-VLRelease Date=Oct 252026.04 | 42.7 | |
| GPT-4oRelease Date=May 242026.04 | 42.6 | |
| OneThinkerRelease Date=Dec 252026.04 | 42.6 | |
| VideoChat-R1.5Release Date=Sep 252026.04 | 40.8 | |
| VideoRFTRelease Date=May 252026.04 | 39.3 | |
| Qwen2.5-VLRelease Date=Feb 252026.04 | 38.3 | |
| VideoChat-R1Release Date=Apr 252026.04 | 38.2 | |
| Open-o3-videoRelease Date=Oct 252026.04 | 37.5 | |
| Video-R1Release Date=Mar 252026.04 | 35.5 |