Multilingual Multimodal Understanding on Multilingual MMBench
70Accuracy (ar)jina-vlm
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| jina-vlm2025.12 | 70 | 75.9 | 78.8 | 74.7 | 75.3 | 71.1 | 74.3 | |
| Qwen2-VL-2Bparameters=2B2025.12 | 66.7 | 67 | 71.1 | 72.1 | 69.9 | 69.3 | 69.4 | |
| InternVL3-2Bparameters=2B2025.12 | 66.4 | 77.8 | 81.3 | 75.9 | 70.7 | 59.5 | 71.9 | |
| Qwen3-VL-2Bparameters=2B, evaluated_by=VLMEvalKit2025.12 | 66.2 | 75.7 | 77.8 | 71.4 | 75.9 | 67 | 72.3 | |
| InternVL3.5-2Bparameters=2B2025.12 | 63.7 | 75.9 | 78.4 | 73.7 | 71.4 | 62 | 70.9 |