Spaces:
Running
Running
| {"Rank":1,"Models":"<a href=\"https:\/\/interestfm-tte.github.io\/\">IFM-TTE-7B<\/a>","Model Size(B)":8.29,"Image-Overall":77.9,"I-CLS":76.74,"I-QA":78.49,"I-RET":74.58,"I-VG":89.3,"VOC2007":83.4,"N24News":82.1,"SUN397":78.8,"ObjectNet":74.0,"Country211":60.5,"Place365":65.5,"ImageNet-1K":84.0,"HatefulMemes":75.1,"ImageNet-A":73.6,"ImageNet-R":90.4,"OK-VQA":83.4,"A-OKVQA":77.3,"DocVQA":95.5,"InfographicsVQA":82.3,"ChartQA":83.2,"Visual7W":73.8,"ScienceQA":67.3,"GQA":79.1,"TextVQA":87.9,"VizWiz":55.1,"VisDial":84.6,"CIRR":66.4,"VisualNews_t2i":79.2,"VisualNews_i2t":82.5,"MSCOCO_t2i":77.7,"MSCOCO_i2t":72.6,"NIGHTS":69.4,"WebQA":91.1,"FashionIQ":32.4,"Wiki-SS-NQ":73.6,"OVEN":69.9,"EDIS":95.5,"MSCOCO":85.4,"RefCOCO":91.7,"RefCOCO-Matching":91.9,"Visual7W-Pointing":88.2} | |
| {"Rank":2,"Models":"<a href=\"https:\/\/seed1-6-embedding.github.io\">seed-1.6-embedding<\/a>","Model Size(B)":"unknown","Image-Overall":77.78,"I-CLS":76.06,"I-QA":73.97,"I-RET":77.9,"I-VG":91.25,"VOC2007":91.9,"N24News":82.9,"SUN397":80.8,"ObjectNet":85.4,"Country211":47.7,"Place365":52.8,"ImageNet-1K":84.2,"HatefulMemes":73.7,"ImageNet-A":73.1,"ImageNet-R":88.1,"OK-VQA":74.2,"A-OKVQA":64.6,"DocVQA":96.2,"InfographicsVQA":82.9,"ChartQA":69.2,"Visual7W":59.6,"ScienceQA":79.2,"GQA":74.7,"TextVQA":85.1,"VizWiz":54.0,"VisDial":84.6,"CIRR":65.0,"VisualNews_t2i":83.4,"VisualNews_i2t":84.5,"MSCOCO_t2i":78.8,"MSCOCO_i2t":77.4,"NIGHTS":72.1,"WebQA":91.7,"FashionIQ":49.0,"Wiki-SS-NQ":79.6,"OVEN":77.2,"EDIS":91.5,"MSCOCO":82.1,"RefCOCO":95.5,"RefCOCO-Matching":93.0,"Visual7W-Pointing":94.4} | |
| {"Rank":3,"Models":"<a href=\"https:\/\/github.com\/360CVGroup\/RzenEmbed\">RzenEmbed-v2-7B<\/a>","Model Size(B)":8.29,"Image-Overall":75.92,"I-CLS":70.61,"I-QA":71.67,"I-RET":78.5,"I-VG":92.1,"VOC2007":91.4,"N24News":84.0,"SUN397":82.7,"ObjectNet":72.0,"Country211":29.7,"Place365":48.1,"ImageNet-1K":84.1,"HatefulMemes":62.4,"ImageNet-A":61.5,"ImageNet-R":90.2,"OK-VQA":73.1,"A-OKVQA":63.1,"DocVQA":94.6,"InfographicsVQA":76.8,"ChartQA":69.2,"Visual7W":63.2,"ScienceQA":60.7,"GQA":74.6,"TextVQA":86.3,"VizWiz":55.1,"VisDial":85.6,"CIRR":67.2,"VisualNews_t2i":82.6,"VisualNews_i2t":85.8,"MSCOCO_t2i":81.1,"MSCOCO_i2t":78.0,"NIGHTS":69.0,"WebQA":92.4,"FashionIQ":41.5,"Wiki-SS-NQ":79.8,"OVEN":81.8,"EDIS":97.2,"MSCOCO":83.5,"RefCOCO":94.9,"RefCOCO-Matching":93.2,"Visual7W-Pointing":96.8} | |
| {"Rank":4,"Models":"<a href=\"https:\/\/github.com\/QQ-MM\/QQMM-embed\">QQMM-embed-v2<\/a>","Model Size(B)":8.29,"Image-Overall":75.28,"I-CLS":72.97,"I-QA":71.85,"I-RET":76.01,"I-VG":87.42,"VOC2007":92.8,"N24News":82.4,"SUN397":83.7,"ObjectNet":74.2,"Country211":30.8,"Place365":48.8,"ImageNet-1K":83.5,"HatefulMemes":79.6,"ImageNet-A":62.7,"ImageNet-R":91.2,"OK-VQA":73.8,"A-OKVQA":71.1,"DocVQA":96.0,"InfographicsVQA":74.0,"ChartQA":68.1,"Visual7W":65.3,"ScienceQA":62.7,"GQA":62.4,"TextVQA":88.2,"VizWiz":56.9,"VisDial":85.5,"CIRR":69.5,"VisualNews_t2i":80.5,"VisualNews_i2t":83.9,"MSCOCO_t2i":82.6,"MSCOCO_i2t":80.1,"NIGHTS":67.0,"WebQA":92.7,"FashionIQ":32.2,"Wiki-SS-NQ":74.2,"OVEN":72.5,"EDIS":91.4,"MSCOCO":81.5,"RefCOCO":93.5,"RefCOCO-Matching":92.9,"Visual7W-Pointing":81.8} | |
| {"Rank":5,"Models":"OEmbedding-v1-7B","Model Size(B)":8.29,"Image-Overall":74.05,"I-CLS":70.56,"I-QA":70.02,"I-RET":74.67,"I-VG":90.97,"VOC2007":89.2,"N24News":82.0,"SUN397":79.0,"ObjectNet":72.6,"Country211":31.2,"Place365":46.0,"ImageNet-1K":84.5,"HatefulMemes":70.5,"ImageNet-A":59.9,"ImageNet-R":90.7,"OK-VQA":73.2,"A-OKVQA":63.3,"DocVQA":95.2,"InfographicsVQA":74.4,"ChartQA":69.4,"Visual7W":60.5,"ScienceQA":54.8,"GQA":68.9,"TextVQA":86.2,"VizWiz":54.3,"VisDial":85.8,"CIRR":65.9,"VisualNews_t2i":82.5,"VisualNews_i2t":86.0,"MSCOCO_t2i":81.7,"MSCOCO_i2t":76.8,"NIGHTS":68.2,"WebQA":90.8,"FashionIQ":25.6,"Wiki-SS-NQ":69.9,"OVEN":73.5,"EDIS":89.4,"MSCOCO":81.8,"RefCOCO":95.6,"RefCOCO-Matching":94.1,"Visual7W-Pointing":92.4} | |
| {"Rank":6,"Models":"ReCo-7B","Model Size(B)":8.29,"Image-Overall":73.87,"I-CLS":70.95,"I-QA":71.52,"I-RET":73.66,"I-VG":87.7,"VOC2007":88.8,"N24News":83.8,"SUN397":81.2,"ObjectNet":74.1,"Country211":28.0,"Place365":47.4,"ImageNet-1K":84.2,"HatefulMemes":73.6,"ImageNet-A":58.3,"ImageNet-R":90.1,"OK-VQA":74.1,"A-OKVQA":61.8,"DocVQA":95.1,"InfographicsVQA":76.3,"ChartQA":66.7,"Visual7W":67.2,"ScienceQA":54.5,"GQA":76.8,"TextVQA":87.3,"VizWiz":55.4,"VisDial":85.3,"CIRR":60.7,"VisualNews_t2i":81.4,"VisualNews_i2t":84.3,"MSCOCO_t2i":79.5,"MSCOCO_i2t":74.0,"NIGHTS":68.7,"WebQA":90.7,"FashionIQ":20.6,"Wiki-SS-NQ":72.1,"OVEN":74.0,"EDIS":92.6,"MSCOCO":74.1,"RefCOCO":93.5,"RefCOCO-Matching":94.1,"Visual7W-Pointing":89.1} | |
| {"Rank":7,"Models":"RzenEmbed-v1-7B","Model Size(B)":8.29,"Image-Overall":73.6,"I-CLS":69.78,"I-QA":68.72,"I-RET":76.83,"I-VG":85.67,"VOC2007":91.6,"N24News":81.7,"SUN397":82.4,"ObjectNet":68.5,"Country211":29.0,"Place365":43.5,"ImageNet-1K":82.8,"HatefulMemes":70.0,"ImageNet-A":59.0,"ImageNet-R":89.3,"OK-VQA":69.6,"A-OKVQA":61.3,"DocVQA":94.8,"InfographicsVQA":73.6,"ChartQA":64.0,"Visual7W":60.5,"ScienceQA":58.2,"GQA":65.5,"TextVQA":86.2,"VizWiz":53.5,"VisDial":83.1,"CIRR":66.3,"VisualNews_t2i":82.6,"VisualNews_i2t":85.8,"MSCOCO_t2i":78.6,"MSCOCO_i2t":76.0,"NIGHTS":68.6,"WebQA":91.3,"FashionIQ":38.7,"Wiki-SS-NQ":74.8,"OVEN":79.6,"EDIS":96.5,"MSCOCO":78.3,"RefCOCO":88.3,"RefCOCO-Matching":85.1,"Visual7W-Pointing":91.0} | |
| {"Rank":8,"Models":"<a href=\"https:\/\/huggingface.co\/OpenSearch-AI\/Ops-MM-embedding-v1-7B\">Ops-MM-embedding-v1-7B<\/a>","Model Size(B)":8.29,"Image-Overall":72.72,"I-CLS":69.65,"I-QA":69.58,"I-RET":73.09,"I-VG":87.15,"VOC2007":84.8,"N24News":82.1,"SUN397":81.0,"ObjectNet":69.7,"Country211":28.5,"Place365":45.6,"ImageNet-1K":81.1,"HatefulMemes":75.7,"ImageNet-A":57.8,"ImageNet-R":90.2,"OK-VQA":70.6,"A-OKVQA":60.0,"DocVQA":94.7,"InfographicsVQA":73.6,"ChartQA":65.2,"Visual7W":58.4,"ScienceQA":49.9,"GQA":79.9,"TextVQA":86.9,"VizWiz":56.6,"VisDial":81.8,"CIRR":55.2,"VisualNews_t2i":80.1,"VisualNews_i2t":84.3,"MSCOCO_t2i":79.3,"MSCOCO_i2t":72.1,"NIGHTS":66.2,"WebQA":91.9,"FashionIQ":24.3,"Wiki-SS-NQ":74.3,"OVEN":73.2,"EDIS":94.4,"MSCOCO":73.9,"RefCOCO":90.4,"RefCOCO-Matching":92.7,"Visual7W-Pointing":91.6} | |
| {"Rank":9,"Models":"TCE-v1","Model Size(B)":8.0,"Image-Overall":72.36,"I-CLS":67.89,"I-QA":70.28,"I-RET":72.31,"I-VG":88.85,"VOC2007":91.6,"N24News":81.7,"SUN397":78.8,"ObjectNet":53.8,"Country211":20.2,"Place365":46.4,"ImageNet-1K":81.3,"HatefulMemes":75.4,"ImageNet-A":59.6,"ImageNet-R":90.1,"OK-VQA":71.5,"A-OKVQA":61.4,"DocVQA":95.0,"InfographicsVQA":81.0,"ChartQA":72.0,"Visual7W":57.8,"ScienceQA":58.7,"GQA":69.4,"TextVQA":83.6,"VizWiz":52.4,"VisDial":86.7,"CIRR":57.8,"VisualNews_t2i":77.9,"VisualNews_i2t":81.8,"MSCOCO_t2i":79.0,"MSCOCO_i2t":77.3,"NIGHTS":68.1,"WebQA":89.3,"FashionIQ":25.6,"Wiki-SS-NQ":66.2,"OVEN":65.4,"EDIS":92.6,"MSCOCO":85.2,"RefCOCO":93.7,"RefCOCO-Matching":91.4,"Visual7W-Pointing":85.1} | |
| {"Rank":10,"Models":"<a href=\"https:\/\/github.com\/QQ-MM\/QQMM-embed\">QQMM-embed<\/a>","Model Size(B)":8.297,"Image-Overall":72.175,"I-CLS":70.07,"I-QA":69.52,"I-RET":71.175,"I-VG":87.075,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":11,"Models":"<a href=\"https:\/\/huggingface.co\/raghavlite\/B3_Qwen2_7B\">B3_Qwen2_7B<\/a>","Model Size(B)":8.29,"Image-Overall":72.0,"I-CLS":70.0,"I-QA":66.5,"I-RET":74.1,"I-VG":84.6,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":12,"Models":"<a href=\"https:\/\/github.com\/GaryGuTC\/UniME-v2\">UniME-V2-LLaVA-OneVision-7B<\/a>","Model Size(B)":8.03,"Image-Overall":71.77,"I-CLS":65.64,"I-QA":68.66,"I-RET":73.1,"I-VG":90.85,"VOC2007":92.5,"N24News":66.0,"SUN397":78.8,"ObjectNet":73.2,"Country211":19.0,"Place365":43.8,"ImageNet-1K":78.9,"HatefulMemes":66.1,"ImageNet-A":49.0,"ImageNet-R":89.1,"OK-VQA":71.7,"A-OKVQA":71.5,"DocVQA":92.4,"InfographicsVQA":67.1,"ChartQA":59.2,"Visual7W":62.7,"ScienceQA":55.2,"GQA":69.0,"TextVQA":84.4,"VizWiz":53.4,"VisDial":84.8,"CIRR":67.0,"VisualNews_t2i":77.3,"VisualNews_i2t":80.1,"MSCOCO_t2i":80.0,"MSCOCO_i2t":74.6,"NIGHTS":68.3,"WebQA":90.2,"FashionIQ":27.0,"Wiki-SS-NQ":70.9,"OVEN":68.5,"EDIS":88.5,"MSCOCO":81.3,"RefCOCO":95.3,"RefCOCO-Matching":92.8,"Visual7W-Pointing":94.0} | |
| {"Rank":13,"Models":"<a href=\"https:\/\/huggingface.co\/zhibinlan\/UME-R1-7B\">UME-R1-7B<\/a>","Model Size(B)":8.29,"Image-Overall":71.25,"I-CLS":67.09,"I-QA":69.18,"I-RET":71.9,"I-VG":84.85,"VOC2007":90.8,"N24News":82.3,"SUN397":80.3,"ObjectNet":42.3,"Country211":25.0,"Place365":46.8,"ImageNet-1K":80.4,"HatefulMemes":79.0,"ImageNet-A":53.9,"ImageNet-R":90.1,"OK-VQA":71.7,"A-OKVQA":58.7,"DocVQA":93.8,"InfographicsVQA":79.2,"ChartQA":75.1,"Visual7W":55.2,"ScienceQA":53.7,"GQA":69.3,"TextVQA":83.5,"VizWiz":51.6,"VisDial":80.7,"CIRR":55.3,"VisualNews_t2i":76.8,"VisualNews_i2t":82.0,"MSCOCO_t2i":78.3,"MSCOCO_i2t":71.4,"NIGHTS":68.1,"WebQA":90.9,"FashionIQ":23.4,"Wiki-SS-NQ":72.5,"OVEN":71.4,"EDIS":92.0,"MSCOCO":72.7,"RefCOCO":91.4,"RefCOCO-Matching":91.1,"Visual7W-Pointing":84.2} | |
| {"Rank":14,"Models":"<a href=\"https:\/\/huggingface.co\/DeepGlint-AI\/UniME-LLaVA-OneVision-7B\">UniME(LLaVA-OneVision-7B-LoRA-Res336)<\/a>","Model Size(B)":8.03,"Image-Overall":70.7,"I-CLS":66.8,"I-QA":66.6,"I-RET":70.5,"I-VG":90.9,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":15,"Models":"<a href=\"https:\/\/huggingface.co\/zhibinlan\/LLaVE-7B\">LLaVE-7B<\/a>","Model Size(B)":8.03,"Image-Overall":70.3,"I-CLS":65.7,"I-QA":65.4,"I-RET":70.9,"I-VG":91.9,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":16,"Models":"<a href=\"https:\/\/huggingface.co\/friedrichor\/Unite-Instruct-Qwen2-VL-7B\">UNITE-Instruct-7B<\/a>","Model Size(B)":8.29,"Image-Overall":70.3,"I-CLS":68.3,"I-QA":65.1,"I-RET":71.6,"I-VG":84.8,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":17,"Models":"<a href=\"https:\/\/huggingface.co\/intfloat\/mmE5-mllama-11b-instruct\">mmE5-mllama-11b-instruct<\/a>","Model Size(B)":10.6,"Image-Overall":69.8,"I-CLS":67.6,"I-QA":62.6,"I-RET":71.0,"I-VG":89.6,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":18,"Models":"<a href=\"https:\/\/arxiv.org\/pdf\/2503.19900\">interestFM-UIR-CAFe-7B<\/a>","Model Size(B)":8.03,"Image-Overall":69.8,"I-CLS":65.2,"I-QA":65.6,"I-RET":70.0,"I-VG":91.2,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":19,"Models":"<a href=\"https:\/\/huggingface.co\/BAAI\/BGE-VL-v1.5-mmeb\">BGE-VL-v1.5 (FT; LlaVA-1.6-Mistral)<\/a>","Model Size(B)":7.57,"Image-Overall":69.4,"I-CLS":63.7,"I-QA":64.9,"I-RET":72.2,"I-VG":86.6,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":20,"Models":"<a href=\"https:\/\/huggingface.co\/OpenSearch-AI\/Ops-MM-embedding-v1-2B\">Ops-MM-embedding-v1-2B<\/a>","Model Size(B)":2.21,"Image-Overall":69.03,"I-CLS":68.07,"I-QA":65.11,"I-RET":69.17,"I-VG":80.85,"VOC2007":81.3,"N24News":78.4,"SUN397":80.7,"ObjectNet":68.4,"Country211":28.6,"Place365":43.9,"ImageNet-1K":81.1,"HatefulMemes":74.0,"ImageNet-A":53.1,"ImageNet-R":91.2,"OK-VQA":64.1,"A-OKVQA":54.0,"DocVQA":93.0,"InfographicsVQA":65.3,"ChartQA":56.1,"Visual7W":58.5,"ScienceQA":47.3,"GQA":74.4,"TextVQA":83.1,"VizWiz":55.3,"VisDial":79.4,"CIRR":47.3,"VisualNews_t2i":76.2,"VisualNews_i2t":79.1,"MSCOCO_t2i":74.1,"MSCOCO_i2t":69.7,"NIGHTS":66.1,"WebQA":91.1,"FashionIQ":18.5,"Wiki-SS-NQ":68.8,"OVEN":69.1,"EDIS":90.6,"MSCOCO":66.8,"RefCOCO":84.1,"RefCOCO-Matching":87.9,"Visual7W-Pointing":84.6} | |
| {"Rank":21,"Models":"RzenEmbed-v1-2B","Model Size(B)":2.21,"Image-Overall":68.53,"I-CLS":65.29,"I-QA":61.7,"I-RET":73.81,"I-VG":77.85,"VOC2007":89.6,"N24News":74.0,"SUN397":78.4,"ObjectNet":71.3,"Country211":24.5,"Place365":41.3,"ImageNet-1K":80.9,"HatefulMemes":58.6,"ImageNet-A":49.5,"ImageNet-R":84.8,"OK-VQA":60.0,"A-OKVQA":53.2,"DocVQA":90.5,"InfographicsVQA":59.3,"ChartQA":51.8,"Visual7W":57.1,"ScienceQA":47.5,"GQA":60.4,"TextVQA":83.8,"VizWiz":53.4,"VisDial":79.1,"CIRR":62.7,"VisualNews_t2i":78.0,"VisualNews_i2t":81.4,"MSCOCO_t2i":76.7,"MSCOCO_i2t":73.6,"NIGHTS":67.9,"WebQA":91.0,"FashionIQ":33.8,"Wiki-SS-NQ":74.9,"OVEN":74.6,"EDIS":92.0,"MSCOCO":68.5,"RefCOCO":86.0,"RefCOCO-Matching":74.8,"Visual7W-Pointing":82.1} | |
| {"Rank":22,"Models":"<a href=\"https:\/\/huggingface.co\/raghavlite\/B3_Qwen2_2B\">B3_Qwen2_2B<\/a>","Model Size(B)":2.21,"Image-Overall":68.1,"I-CLS":67.0,"I-QA":61.19,"I-RET":70.85,"I-VG":79.88,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":23,"Models":"<a href=\"https:\/\/arxiv.org\/abs\/2503.19900\">interestFM-UIR-CAFe-7B<\/a>","Model Size(B)":8.03,"Image-Overall":67.56,"I-CLS":63.63,"I-QA":61.66,"I-RET":69.07,"I-VG":87.58,"VOC2007":89.8,"N24News":83.2,"SUN397":79.9,"ObjectNet":22.5,"Country211":16.7,"Place365":45.0,"ImageNet-1K":77.3,"HatefulMemes":78.7,"ImageNet-A":55.2,"ImageNet-R":88.0,"OK-VQA":67.3,"A-OKVQA":63.8,"DocVQA":79.2,"InfographicsVQA":53.3,"ChartQA":48.8,"Visual7W":52.5,"ScienceQA":65.4,"GQA":65.7,"TextVQA":76.8,"VizWiz":43.8,"VisDial":82.7,"CIRR":60.4,"VisualNews_t2i":69.5,"VisualNews_i2t":79.4,"MSCOCO_t2i":75.4,"MSCOCO_i2t":73.1,"NIGHTS":66.7,"WebQA":89.3,"FashionIQ":39.0,"Wiki-SS-NQ":61.2,"OVEN":60.8,"EDIS":71.3,"MSCOCO":84.7,"RefCOCO":89.4,"RefCOCO-Matching":83.0,"Visual7W-Pointing":93.2} | |
| {"Rank":24,"Models":"<a href=\"https:\/\/huggingface.co\/DeepGlint-AI\/UniME-LLaVA-1.6-7B\">UniME(LLaVA-1.6-7B-LoRA-LowRes)<\/a>","Model Size(B)":7.57,"Image-Overall":66.6,"I-CLS":60.6,"I-QA":52.9,"I-RET":67.9,"I-VG":85.1,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":25,"Models":"<a href=\"https:\/\/huggingface.co\/zhibinlan\/UME-R1-2B\">UME-R1-2B<\/a>","Model Size(B)":2.21,"Image-Overall":66.56,"I-CLS":64.81,"I-QA":62.78,"I-RET":67.62,"I-VG":77.17,"VOC2007":80.0,"N24News":81.1,"SUN397":79.4,"ObjectNet":52.0,"Country211":23.4,"Place365":42.6,"ImageNet-1K":75.3,"HatefulMemes":75.2,"ImageNet-A":50.4,"ImageNet-R":88.7,"OK-VQA":62.4,"A-OKVQA":51.1,"DocVQA":92.2,"InfographicsVQA":67.7,"ChartQA":64.9,"Visual7W":54.1,"ScienceQA":42.7,"GQA":67.3,"TextVQA":78.6,"VizWiz":46.8,"VisDial":76.6,"CIRR":53.7,"VisualNews_t2i":71.7,"VisualNews_i2t":74.2,"MSCOCO_t2i":75.1,"MSCOCO_i2t":68.9,"NIGHTS":67.2,"WebQA":90.0,"FashionIQ":17.1,"Wiki-SS-NQ":62.0,"OVEN":66.9,"EDIS":88.0,"MSCOCO":69.5,"RefCOCO":83.3,"RefCOCO-Matching":84.4,"Visual7W-Pointing":71.5} | |
| {"Rank":26,"Models":"<a href=\"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-Qwen2VL-7B\">VLM2Vec (Qwen2-VL-7B-LoRA-HighRes)<\/a>","Model Size(B)":8.29,"Image-Overall":65.8,"I-CLS":62.6,"I-QA":57.8,"I-RET":69.9,"I-VG":81.7,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":27,"Models":"<a href=\"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-Qwen2VL-7B\">VLM2Vec-V1-Qwen2VL-7B<\/a>","Model Size(B)":8.29,"Image-Overall":65.49,"I-CLS":62.69,"I-QA":56.85,"I-RET":69.44,"I-VG":82.22,"VOC2007":80.7,"N24News":79.7,"SUN397":77.4,"ObjectNet":40.1,"Country211":29.8,"Place365":37.4,"ImageNet-1K":80.1,"HatefulMemes":69.7,"ImageNet-A":58.1,"ImageNet-R":73.9,"OK-VQA":56.8,"A-OKVQA":47.3,"DocVQA":89.7,"InfographicsVQA":60.0,"ChartQA":56.9,"Visual7W":52.7,"ScienceQA":38.5,"GQA":55.1,"TextVQA":71.6,"VizWiz":39.9,"VisDial":81.9,"CIRR":51.1,"VisualNews_t2i":80.5,"VisualNews_i2t":81.2,"MSCOCO_t2i":77.2,"MSCOCO_i2t":73.9,"NIGHTS":67.6,"WebQA":88.3,"FashionIQ":17.1,"Wiki-SS-NQ":62.3,"OVEN":66.5,"EDIS":85.7,"MSCOCO":75.7,"RefCOCO":87.6,"RefCOCO-Matching":84.6,"Visual7W-Pointing":81.0} | |
| {"Rank":28,"Models":"<a href=\"https:\/\/huggingface.co\/zhibinlan\/LLaVE-2B\">LLaVE-2B<\/a>","Model Size(B)":1.95,"Image-Overall":65.2,"I-CLS":62.1,"I-QA":60.2,"I-RET":65.2,"I-VG":84.9,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":29,"Models":"<a href=\"https:\/\/huggingface.co\/VLM2Vec\/VLM2Vec-V2.0\">VLM2Vec-V2.0-Qwen2VL-2B<\/a>","Model Size(B)":2.21,"Image-Overall":64.85,"I-CLS":62.9,"I-QA":56.29,"I-RET":69.47,"I-VG":77.3,"VOC2007":85.0,"N24News":72.9,"SUN397":71.0,"ObjectNet":65.2,"Country211":25.2,"Place365":35.9,"ImageNet-1K":80.8,"HatefulMemes":56.3,"ImageNet-A":47.4,"ImageNet-R":89.3,"OK-VQA":51.5,"A-OKVQA":43.6,"DocVQA":90.1,"InfographicsVQA":58.8,"ChartQA":47.4,"Visual7W":52.9,"ScienceQA":38.2,"GQA":64.9,"TextVQA":72.2,"VizWiz":43.3,"VisDial":82.7,"CIRR":57.5,"VisualNews_t2i":74.5,"VisualNews_i2t":78.2,"MSCOCO_t2i":75.3,"MSCOCO_i2t":71.4,"NIGHTS":68.6,"WebQA":90.6,"FashionIQ":19.5,"Wiki-SS-NQ":66.9,"OVEN":64.3,"EDIS":84.1,"MSCOCO":67.1,"RefCOCO":87.1,"RefCOCO-Matching":85.8,"Visual7W-Pointing":69.2} | |
| {"Rank":30,"Models":"<a href=\"https:\/\/huggingface.co\/DeepGlint-AI\/UniME-Phi3.5-V-4.2B\">UniME(Phi-3.5-V-LoRA)<\/a>","Model Size(B)":4.2,"Image-Overall":64.2,"I-CLS":54.8,"I-QA":55.9,"I-RET":64.5,"I-VG":81.8,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":31,"Models":"<a href=\"https:\/\/huggingface.co\/JUNJIE99\/MMRet-large\">MMRet-MLLM (FT)<\/a>","Model Size(B)":7.57,"Image-Overall":64.1,"I-CLS":56.0,"I-QA":57.4,"I-RET":69.9,"I-VG":83.6,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":32,"Models":"<a href=\"https:\/\/huggingface.co\/friedrichor\/Unite-Instruct-Qwen2-VL-2B\">UNITE-Instruct-2B<\/a>","Model Size(B)":2.21,"Image-Overall":63.3,"I-CLS":63.2,"I-QA":55.9,"I-RET":65.4,"I-VG":75.6,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":33,"Models":"<a href=\"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-LLaVa-Next\">VLM2Vec (LLaVA-1.6-LoRA-HighRes)<\/a>","Model Size(B)":7.57,"Image-Overall":62.9,"I-CLS":61.2,"I-QA":49.9,"I-RET":67.4,"I-VG":86.1,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":34,"Models":"<a href=\"https:\/\/huggingface.co\/BAAI\/BGE-VL-v1.5-zs\">BGE-VL-v1.5 (zeroshot; LlaVA-1.6-Mistral)<\/a>","Model Size(B)":7.57,"Image-Overall":60.1,"I-CLS":56.1,"I-QA":55.3,"I-RET":63.9,"I-VG":70.8,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":35,"Models":"<a href=\"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-Full\">VLM2Vec (Phi-3.5-V-LoRA)<\/a>","Model Size(B)":4.15,"Image-Overall":60.1,"I-CLS":54.8,"I-QA":54.9,"I-RET":62.3,"I-VG":79.5,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":36,"Models":"<a href=\"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-Qwen2VL-2B\">VLM2Vec-V1-Qwen2VL-2B<\/a>","Model Size(B)":2.21,"Image-Overall":59.74,"I-CLS":58.71,"I-QA":49.26,"I-RET":64.98,"I-VG":72.85,"VOC2007":74.3,"N24News":73.7,"SUN397":73.8,"ObjectNet":37.1,"Country211":21.5,"Place365":35.3,"ImageNet-1K":77.5,"HatefulMemes":58.3,"ImageNet-A":50.9,"ImageNet-R":84.7,"OK-VQA":48.5,"A-OKVQA":39.5,"DocVQA":82.5,"InfographicsVQA":47.7,"ChartQA":42.3,"Visual7W":51.2,"ScienceQA":30.7,"GQA":48.3,"TextVQA":63.3,"VizWiz":38.6,"VisDial":74.3,"CIRR":46.8,"VisualNews_t2i":73.1,"VisualNews_i2t":73.7,"MSCOCO_t2i":73.4,"MSCOCO_i2t":68.5,"NIGHTS":66.3,"WebQA":85.9,"FashionIQ":14.0,"Wiki-SS-NQ":54.2,"OVEN":68.3,"EDIS":81.2,"MSCOCO":66.5,"RefCOCO":80.9,"RefCOCO-Matching":75.7,"Visual7W-Pointing":68.3} | |
| {"Rank":37,"Models":"<a href=\"https:\/\/arxiv.org\/pdf\/2503.19900\">interestFM-UIR-CAFe-0.5B<\/a>","Model Size(B)":0.894,"Image-Overall":59.6,"I-CLS":59.1,"I-QA":49.1,"I-RET":61.0,"I-VG":83.0,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":38,"Models":"<a href=\"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-Qwen2VL-2B\">VLM2Vec (Qwen2-VL-2B-LoRA-HighRes)<\/a>","Model Size(B)":2.21,"Image-Overall":59.3,"I-CLS":59.0,"I-QA":49.4,"I-RET":65.4,"I-VG":73.4,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":39,"Models":"<a href=\"https:\/\/huggingface.co\/zhibinlan\/LLaVE-0.5B\">LLaVE-0.5B<\/a>","Model Size(B)":0.894,"Image-Overall":59.1,"I-CLS":57.4,"I-QA":50.3,"I-RET":59.8,"I-VG":82.9,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":40,"Models":"<a href=\"https:\/\/huggingface.co\/intfloat\/mmE5-mllama-11b-instruct\">mmE5 (w\/ 560K synthetic data)<\/a>","Model Size(B)":10.6,"Image-Overall":58.6,"I-CLS":60.6,"I-QA":55.7,"I-RET":54.7,"I-VG":72.4,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":41,"Models":"<a href=\"https:\/\/huggingface.co\/Alibaba-NLP\/gme-Qwen2-VL-7B-Instruct\">gme-Qwen2-VL-7B-Instruct<\/a>","Model Size(B)":8.29,"Image-Overall":55.95,"I-CLS":57.65,"I-QA":34.66,"I-RET":71.17,"I-VG":59.3,"VOC2007":80.3,"N24News":50.5,"SUN397":69.5,"ObjectNet":69.0,"Country211":24.8,"Place365":39.1,"ImageNet-1K":64.6,"HatefulMemes":53.6,"ImageNet-A":41.2,"ImageNet-R":83.9,"OK-VQA":33.2,"A-OKVQA":21.0,"DocVQA":41.4,"InfographicsVQA":20.3,"ChartQA":17.8,"Visual7W":22.2,"ScienceQA":28.0,"GQA":76.9,"TextVQA":46.8,"VizWiz":39.0,"VisDial":60.8,"CIRR":54.9,"VisualNews_t2i":79.7,"VisualNews_i2t":83.6,"MSCOCO_t2i":71.2,"MSCOCO_i2t":57.7,"NIGHTS":67.6,"WebQA":91.4,"FashionIQ":37.8,"Wiki-SS-NQ":78.2,"OVEN":75.1,"EDIS":96.0,"MSCOCO":31.4,"RefCOCO":60.9,"RefCOCO-Matching":78.4,"Visual7W-Pointing":66.5} | |
| {"Rank":42,"Models":"<a href=\"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-Full\">VLM2Vec (Phi-3.5-V-FT)<\/a>","Model Size(B)":4.15,"Image-Overall":55.9,"I-CLS":52.8,"I-QA":50.3,"I-RET":57.8,"I-VG":72.3,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":43,"Models":"<a href=\"https:\/\/huggingface.co\/Alibaba-NLP\/gme-Qwen2-VL-2B-Instruct\">gme-Qwen2-VL-2B-Instruct<\/a>","Model Size(B)":2.21,"Image-Overall":55.8,"I-CLS":56.9,"I-QA":41.2,"I-RET":67.8,"I-VG":53.4,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":44,"Models":"<a href=\"https:\/\/arxiv.org\/abs\/2503.19900\">interestFM-UIR-CAFe-0.5B<\/a>","Model Size(B)":0.894,"Image-Overall":55.43,"I-CLS":56.44,"I-QA":45.28,"I-RET":57.55,"I-VG":71.95,"VOC2007":81.9,"N24News":69.6,"SUN397":68.8,"ObjectNet":51.0,"Country211":11.3,"Place365":37.4,"ImageNet-1K":64.6,"HatefulMemes":55.3,"ImageNet-A":38.1,"ImageNet-R":86.4,"OK-VQA":47.1,"A-OKVQA":43.0,"DocVQA":60.6,"InfographicsVQA":30.2,"ChartQA":32.7,"Visual7W":48.9,"ScienceQA":39.7,"GQA":52.1,"TextVQA":59.6,"VizWiz":38.9,"VisDial":68.4,"CIRR":43.4,"VisualNews_t2i":58.4,"VisualNews_i2t":61.0,"MSCOCO_t2i":66.4,"MSCOCO_i2t":63.2,"NIGHTS":63.8,"WebQA":80.0,"FashionIQ":23.3,"Wiki-SS-NQ":46.4,"OVEN":52.4,"EDIS":63.9,"MSCOCO":63.1,"RefCOCO":76.6,"RefCOCO-Matching":70.6,"Visual7W-Pointing":77.5} | |
| {"Rank":45,"Models":"<a href=\"https:\/\/huggingface.co\/TIGER-Lab\/VLM2Vec-LLaVa-Next\">VLM2Vec (LLaVA-1.6-LoRA-LowRes)<\/a>","Model Size(B)":7.57,"Image-Overall":55.0,"I-CLS":54.7,"I-QA":50.3,"I-RET":56.2,"I-VG":64.0,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":46,"Models":"<a href=\"https:\/\/huggingface.co\/code-kunkun\/LamRA-Ret\">LamRA-Ret<\/a>","Model Size(B)":8.29,"Image-Overall":54.08,"I-CLS":59.2,"I-QA":26.47,"I-RET":69.95,"I-VG":62.65,"VOC2007":80.1,"N24News":51.3,"SUN397":68.5,"ObjectNet":66.4,"Country211":28.3,"Place365":40.6,"ImageNet-1K":72.3,"HatefulMemes":49.0,"ImageNet-A":47.0,"ImageNet-R":88.5,"OK-VQA":37.8,"A-OKVQA":27.0,"DocVQA":22.3,"InfographicsVQA":16.5,"ChartQA":11.7,"Visual7W":19.6,"ScienceQA":26.3,"GQA":38.5,"TextVQA":33.0,"VizWiz":32.0,"VisDial":61.3,"CIRR":51.7,"VisualNews_t2i":70.4,"VisualNews_i2t":83.9,"MSCOCO_t2i":72.2,"MSCOCO_i2t":73.7,"NIGHTS":65.6,"WebQA":81.0,"FashionIQ":42.0,"Wiki-SS-NQ":69.7,"OVEN":82.0,"EDIS":85.9,"MSCOCO":44.8,"RefCOCO":62.8,"RefCOCO-Matching":75.7,"Visual7W-Pointing":67.3} | |
| {"Rank":47,"Models":"<a href=\"https:\/\/huggingface.co\/code-kunkun\/LamRA-Ret-Qwen2.5VL-7b\">LamRA-Ret-Qwen2.5VL-7b<\/a>","Model Size(B)":8.29,"Image-Overall":52.43,"I-CLS":51.7,"I-QA":34.12,"I-RET":66.86,"I-VG":56.73,"VOC2007":78.7,"N24News":29.8,"SUN397":66.5,"ObjectNet":59.4,"Country211":21.7,"Place365":37.4,"ImageNet-1K":58.9,"HatefulMemes":51.3,"ImageNet-A":36.3,"ImageNet-R":77.0,"OK-VQA":39.9,"A-OKVQA":34.1,"DocVQA":37.1,"InfographicsVQA":23.7,"ChartQA":15.0,"Visual7W":24.6,"ScienceQA":31.3,"GQA":57.4,"TextVQA":46.1,"VizWiz":32.0,"VisDial":62.5,"CIRR":44.7,"VisualNews_t2i":70.1,"VisualNews_i2t":74.2,"MSCOCO_t2i":65.7,"MSCOCO_i2t":71.1,"NIGHTS":64.4,"WebQA":85.7,"FashionIQ":33.4,"Wiki-SS-NQ":67.0,"OVEN":84.8,"EDIS":78.7,"MSCOCO":36.0,"RefCOCO":57.1,"RefCOCO-Matching":82.6,"Visual7W-Pointing":51.2} | |
| {"Rank":48,"Models":"<a href=\"https:\/\/huggingface.co\/Alibaba-NLP\/gme-Qwen2-VL-2B-Instruct\">gme-Qwen2-VL-2B-Instruct<\/a>","Model Size(B)":2.21,"Image-Overall":51.89,"I-CLS":54.44,"I-QA":29.86,"I-RET":66.93,"I-VG":55.47,"VOC2007":75.9,"N24News":50.1,"SUN397":67.3,"ObjectNet":70.6,"Country211":26.5,"Place365":35.8,"ImageNet-1K":58.3,"HatefulMemes":52.5,"ImageNet-A":28.8,"ImageNet-R":78.6,"OK-VQA":29.9,"A-OKVQA":18.6,"DocVQA":29.8,"InfographicsVQA":11.6,"ChartQA":13.4,"Visual7W":16.2,"ScienceQA":27.3,"GQA":75.1,"TextVQA":39.7,"VizWiz":37.0,"VisDial":48.1,"CIRR":44.2,"VisualNews_t2i":74.7,"VisualNews_i2t":78.3,"MSCOCO_t2i":68.1,"MSCOCO_i2t":63.1,"NIGHTS":67.0,"WebQA":88.8,"FashionIQ":32.9,"Wiki-SS-NQ":73.9,"OVEN":72.3,"EDIS":91.8,"MSCOCO":28.6,"RefCOCO":55.9,"RefCOCO-Matching":73.3,"Visual7W-Pointing":64.1} | |
| {"Rank":49,"Models":"<a href=\"https:\/\/huggingface.co\/nvidia\/MM-Embed\">MM-Embed<\/a>","Model Size(B)":8.18,"Image-Overall":50.0,"I-CLS":48.1,"I-QA":32.3,"I-RET":63.8,"I-VG":57.8,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":50,"Models":"<a href=\"https:\/\/doi.org\/10.48550\/arXiv.2212.07143\">OpenCLIP-FT<\/a>","Model Size(B)":0.428,"Image-Overall":47.2,"I-CLS":56.0,"I-QA":21.9,"I-RET":55.4,"I-VG":64.1,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":51,"Models":"<a href=\"https:\/\/doi.org\/10.48550\/arXiv.2103.00020\">CLIP-FT<\/a>","Model Size(B)":0.428,"Image-Overall":45.4,"I-CLS":55.2,"I-QA":19.7,"I-RET":53.2,"I-VG":62.2,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":52,"Models":"<a href=\"https:\/\/huggingface.co\/TIGER-Lab\/UniIR\">UniIR (CLIP_SF)<\/a>","Model Size(B)":0.428,"Image-Overall":44.7,"I-CLS":44.3,"I-QA":16.2,"I-RET":61.8,"I-VG":65.3,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":53,"Models":"<a href=\"https:\/\/huggingface.co\/JUNJIE99\/MMRet-large\">MMRet-MLLM (LLaVA-1.6)<\/a>","Model Size(B)":7.57,"Image-Overall":44.0,"I-CLS":47.2,"I-QA":18.4,"I-RET":56.5,"I-VG":62.2,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":54,"Models":"<a href=\"https:\/\/huggingface.co\/TIGER-Lab\/UniIR\">UniIR (BLIP_FF)<\/a>","Model Size(B)":0.247,"Image-Overall":42.8,"I-CLS":42.1,"I-QA":15.0,"I-RET":60.1,"I-VG":62.2,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":55,"Models":"<a href=\"https:\/\/github.com\/mlfoundations\/open_clip\">open_clip-ViT-L\/14<\/a>","Model Size(B)":0.428,"Image-Overall":39.7,"I-CLS":47.8,"I-QA":10.9,"I-RET":52.3,"I-VG":53.3,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":56,"Models":"<a href=\"https:\/\/huggingface.co\/openai\/clip-vit-large-patch14\">clip-vit-large-patch14<\/a>","Model Size(B)":0.428,"Image-Overall":37.8,"I-CLS":42.8,"I-QA":9.1,"I-RET":53.0,"I-VG":51.8,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":57,"Models":"<a href=\"https:\/\/huggingface.co\/vidore\/colpali-v1.3\">colpali-v1.3<\/a>","Model Size(B)":2.92,"Image-Overall":34.89,"I-CLS":40.3,"I-QA":11.51,"I-RET":48.05,"I-VG":40.3,"VOC2007":69.8,"N24News":25.5,"SUN397":56.1,"ObjectNet":45.6,"Country211":6.0,"Place365":27.5,"ImageNet-1K":42.4,"HatefulMemes":50.6,"ImageNet-A":14.9,"ImageNet-R":64.6,"OK-VQA":9.4,"A-OKVQA":6.6,"DocVQA":11.3,"InfographicsVQA":5.0,"ChartQA":5.7,"Visual7W":6.1,"ScienceQA":16.3,"GQA":8.3,"TextVQA":18.8,"VizWiz":27.6,"VisDial":41.2,"CIRR":8.2,"VisualNews_t2i":50.1,"VisualNews_i2t":47.6,"MSCOCO_t2i":59.2,"MSCOCO_i2t":49.9,"NIGHTS":65.5,"WebQA":53.8,"FashionIQ":5.9,"Wiki-SS-NQ":80.5,"OVEN":50.0,"EDIS":64.7,"MSCOCO":36.7,"RefCOCO":64.5,"RefCOCO-Matching":3.9,"Visual7W-Pointing":56.1} | |
| {"Rank":58,"Models":"<a href=\"https:\/\/huggingface.co\/google\/siglip-base-patch16-224\">siglip-base-patch16-224<\/a>","Model Size(B)":0.203,"Image-Overall":34.8,"I-CLS":40.3,"I-QA":8.4,"I-RET":31.6,"I-VG":59.5,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":59,"Models":"<a href=\"https:\/\/github.com\/google-deepmind\/magiclens\">Magiclens<\/a>","Model Size(B)":0.428,"Image-Overall":27.8,"I-CLS":38.8,"I-QA":8.3,"I-RET":35.4,"I-VG":26.0,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":60,"Models":"<a href=\"https:\/\/huggingface.co\/Salesforce\/blip2-opt-2.7b\">blip2-opt-2.7b<\/a>","Model Size(B)":3.74,"Image-Overall":25.2,"I-CLS":27.0,"I-QA":4.2,"I-RET":33.9,"I-VG":47.0,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |
| {"Rank":61,"Models":"<a href=\"https:\/\/huggingface.co\/royokong\/e5-v\">e5-v<\/a>","Model Size(B)":8.36,"Image-Overall":13.3,"I-CLS":21.8,"I-QA":4.9,"I-RET":11.5,"I-VG":19.0,"VOC2007":"-","N24News":"-","SUN397":"-","ObjectNet":"-","Country211":"-","Place365":"-","ImageNet-1K":"-","HatefulMemes":"-","ImageNet-A":"-","ImageNet-R":"-","OK-VQA":"-","A-OKVQA":"-","DocVQA":"-","InfographicsVQA":"-","ChartQA":"-","Visual7W":"-","ScienceQA":"-","GQA":"-","TextVQA":"-","VizWiz":"-","VisDial":"-","CIRR":"-","VisualNews_t2i":"-","VisualNews_i2t":"-","MSCOCO_t2i":"-","MSCOCO_i2t":"-","NIGHTS":"-","WebQA":"-","FashionIQ":"-","Wiki-SS-NQ":"-","OVEN":"-","EDIS":"-","MSCOCO":"-","RefCOCO":"-","RefCOCO-Matching":"-","Visual7W-Pointing":"-"} | |