Multimodal Understanding on Multimodal Evaluation Suite Table 4
73.6ALL AVG ScoreGenLIP
Evaluation results
| Method | Links | |
|---|---|---|
| GenLIPArch=g/16, Data=8.0B, Evaluation Protocol=Frozen visual representation, LLM Backbone=LLaVA-NeXT-Qwen2.5-7B2026.05 | 73.6 | |
| GenLIPArch=So/16, Data=8.0B, Evaluation Protocol=Frozen visual representation, LLM Backbone=LLaVA-NeXT-Qwen2.5-7B2026.05 | 71.8 | |
| SigLIP2Arch=So/16, Data=40.0B, Evaluation Protocol=Frozen visual representation, LLM Backbone=LLaVA-NeXT-Qwen2.5-7B2026.05 | 69.4 | |
| GenLIPArch=L/16, Data=8.0B, Evaluation Protocol=Frozen visual representation, LLM Backbone=LLaVA-NeXT-Qwen2.5-7B2026.05 | 69 | |
| SigLIP2Arch=g/16, Data=40.0B, Evaluation Protocol=Frozen visual representation, LLM Backbone=LLaVA-NeXT-Qwen2.5-7B2026.05 | 68.9 | |
| OVision2Arch=L/16, Data=12.8B, Evaluation Protocol=Frozen visual representation, LLM Backbone=LLaVA-NeXT-Qwen2.5-7B2026.05 | 64.9 | |
| SigLIPArch=L/16, Data=40.0B, Evaluation Protocol=Frozen visual representation, LLM Backbone=LLaVA-NeXT-Qwen2.5-7B2026.05 | 64.5 | |
| CLIPArch=L/14, Data=12.8B, Evaluation Protocol=Frozen visual representation, LLM Backbone=LLaVA-NeXT-Qwen2.5-7B2026.05 | 58.8 | |
| AIMv2Arch=L/14, Data=12.0B, Evaluation Protocol=Frozen visual representation, LLM Backbone=LLaVA-NeXT-Qwen2.5-7B2026.05 | 58.6 |