LongVideoBench: Results as Published

LongVideoBench tests understanding of long videos that come with subtitles. It has 3,763 web videos, grouped from a few seconds up to an hour, and 6,678 human-written multiple-choice questions in 17 categories. Each question first points at one or more moments, called the referred context, and then asks what is there or how those moments relate. The reported result is accuracy.

Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.