# Long-video understanding on HourVideo (test) Source: [Long-video understanding on HourVideo (test)]() Collection index: [llms.txt]() Data updated: 2026-03-05T09:48:58.079Z Evaluation of long-video understanding capabilities on the test split of the HourVideo dataset, measured by token efficiency and inference time. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Long-video understanding | | Dataset (including any stated split) | HourVideo (test) | | Metric | Inference Time (s) | | Unit | TIME | | Direction | Lower is better | | Results loaded | 7 of 7 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Inference Time (s)](): Lower is better; unit: TIME. - [Tokens/Frame](): Lower is better; unit: SCALAR. ## Recorded results | Method | Inference Time (s) | Result date | Report paper | | --- | --- | --- | --- | | PSFR | 0.021 | Not recorded | 69a90e062d603e6de3e407f5 | | MaxInfo | 0.038 | Not recorded | 69a90e062d603e6de3e407f5 | | Scene-Caption LLM Selector-s | 0.6 | Not recorded | 69a90e062d603e6de3e407f5 | | ViaRL | 2.6 | Not recorded | 69a90e062d603e6de3e407f5 | | Scene-Caption LLM Selector-m | 2.8 | Not recorded | 69a90e062d603e6de3e407f5 | | ReMEmbR | 80 | Not recorded | 69a90e062d603e6de3e407f5 | | GenS | 103 | Not recorded | 69a90e062d603e6de3e407f5 | ### PSFR Inference Time (s): 0.021. Result ID: 69a951706dbb7075b9533187. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MaxInfo Inference Time (s): 0.038. Result ID: 69a951706dbb7075b9533186. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Scene-Caption LLM Selector-s Inference Time (s): 0.6. Result ID: 69a951706dbb7075b9533184. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of beams":"1"}. This record does not assert independent reproduction. ### ViaRL Inference Time (s): 2.6. Result ID: 69a951706dbb7075b9533183. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of beams":"1"}. This record does not assert independent reproduction. ### Scene-Caption LLM Selector-m Inference Time (s): 2.8. Result ID: 69a951706dbb7075b9533185. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of beams":"5"}. This record does not assert independent reproduction. ### ReMEmbR Inference Time (s): 80. Result ID: 69a951706dbb7075b9533181. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GenS Inference Time (s): 103. Result ID: 69a951706dbb7075b9533182. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of beams":"1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.