Socratic Models

Reported on 2 benchmarks across 2 tasks · 1 paper

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

Computer Vision2 results

VideoonMSR-VTT-1kA
video-to-text R@1· 2022-04-01
42.8
best: 64.8 (HunYuan_tvr (huge))
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language arXiv:2204.00598
Video RetrievalonMSR-VTT-1kA
video-to-text R@1· 2022-04-01
42.8
best: 64.8 (HunYuan_tvr (huge))
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language arXiv:2204.00598