all the models — AI benchmark observatory
← Benchmarks

LongVideoBench

LongVideoBench is a question-answering benchmark featuring video-language interleaved inputs up to an hour long. It includes 3,763 varying-length web-collected videos with subtitles across diverse themes and 6,678 human-annotated multiple-choice questions in 17 fine-grained categories for comprehensive evaluation of long-term multimodal understanding.

id longvideobench · max 1 · 6 models reported

#ModelScore

No scores for this benchmark yet.