Multimodal Perception on RealWorldQA
69.28ScoreQwen2.5-VL
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-VLScale=7B2026.06 | 69.28 | |
| LLaVA-OVScale=1.5-8B2026.06 | 68.1 | |
| Llama-3.2 11B-VisionCheckpoint=base2026.06 | 66.27 | |
| MOSS-Video-PreviewSFT Mode=real-time2026.06 | 60.92 | |
| MOSS-Video-PreviewSFT Mode=offline2026.06 | 59.48 |