# Video Question Answering on TGIF-QA LLaVA-Hound out-of-domain (test) Source: [Video Question Answering on TGIF-QA LLaVA-Hound out-of-domain (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:57.292Z Evaluation of model performance on the out-of-domain test split of the TGIF-QA LLaVA-Hound benchmark for Video Question Answering tasks, reporting accuracy. 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 | Video Question Answering | | Dataset (including any stated split) | TGIF-QA LLaVA-Hound out-of-domain (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MM1.5-Video | 65.5 | Not recorded | 68fa75051e209131cea65504 | | MM1.5-Video | 64.9 | Not recorded | 68fa75051e209131cea65504 | | MM1.5-Video | 64 | Not recorded | 68fa75051e209131cea65504 | | LLAVA-HOUND-SFT | 61.1 | Not recorded | 68fa75051e209131cea65504 | | MM1.5-Video | 49.8 | Not recorded | 68fa75051e209131cea65504 | | MM1.5-Video | 49.2 | Not recorded | 68fa75051e209131cea65504 | | MM1.5-Video | 47.6 | Not recorded | 68fa75051e209131cea65504 | | Chat-UniVi | 33.2 | Not recorded | 68fa75051e209131cea65504 | | Video-LLaVA | 33 | Not recorded | 68fa75051e209131cea65504 | | Video-ChatGPT | 31.4 | Not recorded | 68fa75051e209131cea65504 | | LLaMA-VID | 27.2 | Not recorded | 68fa75051e209131cea65504 | ### MM1.5-Video Accuracy: 65.5. Result ID: 699370673a6c31484915ef6b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"7B","Protocol":"SFT"}. This record does not assert independent reproduction. ### MM1.5-Video Accuracy: 64.9. Result ID: 699370673a6c31484915ef6a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"3B","Protocol":"SFT"}. This record does not assert independent reproduction. ### MM1.5-Video Accuracy: 64. Result ID: 699370673a6c31484915ef69. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"1B","Protocol":"SFT"}. This record does not assert independent reproduction. ### LLAVA-HOUND-SFT Accuracy: 61.1. Result ID: 699370673a6c31484915ef65. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"7B"}. This record does not assert independent reproduction. ### MM1.5-Video Accuracy: 49.8. Result ID: 699370673a6c31484915ef68. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"7B","Protocol":"Training-free"}. This record does not assert independent reproduction. ### MM1.5-Video Accuracy: 49.2. Result ID: 699370673a6c31484915ef67. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"3B","Protocol":"Training-free"}. This record does not assert independent reproduction. ### MM1.5-Video Accuracy: 47.6. Result ID: 699370673a6c31484915ef66. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"1B","Protocol":"Training-free"}. This record does not assert independent reproduction. ### Chat-UniVi Accuracy: 33.2. Result ID: 699370673a6c31484915ef63. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"7B"}. This record does not assert independent reproduction. ### Video-LLaVA Accuracy: 33. Result ID: 699370673a6c31484915ef64. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"7B"}. This record does not assert independent reproduction. ### Video-ChatGPT Accuracy: 31.4. Result ID: 699370673a6c31484915ef61. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"7B"}. This record does not assert independent reproduction. ### LLaMA-VID Accuracy: 27.2. Result ID: 699370673a6c31484915ef62. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.