General & Complex QA on VMME
86.9Overall AccuracyGemini2.5 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini2.5 ProRelease Date=May 252026.04 | 86.9 | |
| GPT-5Release Date=Dec 252026.04 | 86 | |
| GPT-4oRelease Date=May 242026.04 | 77.2 | |
| Gemini1.5 ProRelease Date=Dec 242026.04 | 75 | |
| Omni-o32026.04 | 72.6 | |
| Qwen3-VLRelease Date=Oct 252026.04 | 72.5 | |
| Qwen3-OmniRelease Date=Sep 252026.04 | 70.5 | |
| OlaRelease Date=Feb 252026.04 | 68.4 | |
| OneThinkerRelease Date=Dec 252026.04 | 66.5 | |
| HumanOmniV2Release Date=June 252026.04 | 66 | |
| VideoChat-R1.5Release Date=Sep 252026.04 | 65.2 | |
| VideoRFTRelease Date=May 252026.04 | 65.2 | |
| Qwen2.5-VLRelease Date=Feb 252026.04 | 65.1 | |
| Open-o3-videoRelease Date=Oct 252026.04 | 63.6 | |
| AVATARSource=CVPR 262026.04 | 62.8 | |
| EchoInk-R1Release Date=May 252026.04 | 60.8 | |
| Omni-R1Release Date=May 252026.04 | 60.7 | |
| VideoChat-R1Release Date=Apr 252026.04 | 59.8 | |
| Qwen2.5-OmniRelease Date=Mar 252026.04 | 59.8 | |
| Video-R1Release Date=Mar 252026.04 | 59.3 | |
| AV-ReasonerRelease Date=June 252026.04 | 56.8 |