Multi-choice Question Answering on SEED-IMG
76.5AccuracyQwen2 VL
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2 VLModel Scale=7B, Model Modality Type=Vision-language2024.10 | 76.5 | |
| Baichuan-omniModel Scale=7B, Model Modality Type=Omni-modal2024.10 | 74.1 | |
| VITAModel Scale=8x7B, Model Modality Type=Omni-modal2024.10 | 72.6 | |
| MiniCPM-Llama3-V 2.5Model Scale=8B, Model Modality Type=Vision-language2024.10 | 72.4 |