Omnimodal common event understanding on Daily-Omni
81.4AccuracyGemini-2.5-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-2.5-ProModel Accessibility=Proprietary2026.05 | 81.4 | |
| Gemini-2.0-FlashModel Accessibility=Proprietary2026.05 | 67.8 | |
| LatentOmniModel Accessibility=Open-source, Training/Reasoning Strategy=Latent reasoning2026.05 | 67.4 | |
| OmniVinciModel Accessibility=Open-source2026.05 | 66.5 | |
| Qwen2.5-Omni-7B + Explicit Text CoTModel Accessibility=Open-source, Training/Reasoning Strategy=Explicit Text CoT2026.05 | 65.6 | |
| Qwen2.5-Omni-7BModel Accessibility=Open-source, Training/Reasoning Strategy=Base2026.05 | 62.9 | |
| Qwen2.5-Omni-7B + Vanilla SFTModel Accessibility=Open-source, Training/Reasoning Strategy=Vanilla SFT2026.05 | 62 | |
| HumanOmniV2-7BModel Accessibility=Open-source2026.05 | 58.5 | |
| GPT-4oModel Accessibility=Proprietary2026.05 | 56.5 | |
| MiniCPM-o-7BModel Accessibility=Open-source2026.05 | 53.1 | |
| Baichuan-Omni-1.5Model Accessibility=Open-source2026.05 | 50 | |
| VITA-1.5-7BModel Accessibility=Open-source2026.05 | 44.7 | |
| VideoLLaMA2-7BModel Accessibility=Open-source2026.05 | 35.2 |