Visual Commonsense Reasoning On Gd Vcr
评估指标
Accuracy
Gap (West)
评测结果
各个模型在此基准测试上的表现结果
比较表格
模型名称 | Accuracy | Gap (West) |
---|---|---|
broaden-the-vision-geo-diverse-visual | 53.95 | -10.42 |
broaden-the-vision-geo-diverse-visual | 88.84 | - |
broaden-the-vision-geo-diverse-visual | 59.99 | -7.28 |
broaden-the-vision-geo-diverse-visual | 35.33 | - |