Sevila (4B)

Reported on 2 benchmarks across 2 tasks · 1 paper · 1 SOTA

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

Natural Language Processing1 result

Question AnsweringonNExT-QA
Accuracy· 2023-05-11
63.6
best: 79.6 (VideoMultiAgent (GPT-4o))
SOTA
Self-Chained Image-Language Model for Video Localization and Question Answering arXiv:2305.06988

Reasoning1 result

Video Question AnsweringonNExT-QA
Accuracy· 2023-05-11
63.6
best: 85.5 (LinVT-Qwen2-VL (7B))
Self-Chained Image-Language Model for Video Localization and Question Answering arXiv:2305.06988