Human & BLIP2

Reported on 3 benchmarks across 1 task

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Image RetrievalonVisDial
Recall@10 on 1 rounds
67
best: 70 (ChatGPT & BLIP2)
Image RetrievalonVisDial
Recall@10 on 2 rounds
70
best: 73.5 (ChatGPT & BLIP2)
Image RetrievalonVisDial
Recall@10 on 3 rounds
71.8
best: 75.75 (ChatGPT & BLIP2)