# Video Description on DREAM-1K Live-action 1.0 (test) Source: [Video Description on DREAM-1K Live-action 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:43:23.305Z Evaluation of Video Description performance on the test split of the DREAM-1K Live-action 1.0 dataset, measured using F1, Precision, and Recall. 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 Description | | Dataset (including any stated split) | DREAM-1K Live-action 1.0 (test) | | Metric | F1 Score | | 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 - [F1 Score](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | Tarsier2-7B | 43.8 | Not recorded | 68fa74e41e209131cea64782 | | GPT-4o | 39.8 | Not recorded | 68fa74e41e209131cea64782 | | Tarsier-34B | 38.5 | Not recorded | 68fa74e41e209131cea64782 | | Tarsier-7B | 36.6 | Not recorded | 68fa74e41e209131cea64782 | | Gemini 1.5 Pro | 36.4 | Not recorded | 68fa74e41e209131cea64782 | | GPT-4V | 34.8 | Not recorded | 68fa74e41e209131cea64782 | | PLLAVA-34B | 29.3 | Not recorded | 68fa74e41e209131cea64782 | | VideoChat2 | 26 | Not recorded | 68fa74e41e209131cea64782 | | LLaVA-NeXT-Video | 25.8 | Not recorded | 68fa74e41e209131cea64782 | | MiniGPT-4V+ | 23.6 | Not recorded | 68fa74e41e209131cea64782 | | Video-LLaVA | 19.4 | Not recorded | 68fa74e41e209131cea64782 | ### Tarsier2-7B F1 Score: 43.8. Result ID: 69937e533a6c3148491656ce. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Tarsier2-7B"}. This record does not assert independent reproduction. ### GPT-4o F1 Score: 39.8. Result ID: 69937e533a6c3148491656cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction. ### Tarsier-34B F1 Score: 38.5. Result ID: 69937e533a6c3148491656cd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Tarsier-34B"}. This record does not assert independent reproduction. ### Tarsier-7B F1 Score: 36.6. Result ID: 69937e533a6c3148491656cc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Tarsier-7B"}. This record does not assert independent reproduction. ### Gemini 1.5 Pro F1 Score: 36.4. Result ID: 69937e533a6c3148491656ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini 1.5 Pro"}. This record does not assert independent reproduction. ### GPT-4V F1 Score: 34.8. Result ID: 69937e533a6c3148491656c9. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-4V"}. This record does not assert independent reproduction. ### PLLAVA-34B F1 Score: 29.3. Result ID: 69937e533a6c3148491656c8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"PLLAVA-34B"}. This record does not assert independent reproduction. ### VideoChat2 F1 Score: 26. Result ID: 69937e533a6c3148491656c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VideoChat2-Mistral"}. This record does not assert independent reproduction. ### LLaVA-NeXT-Video F1 Score: 25.8. Result ID: 69937e533a6c3148491656c6. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaVA-NeXT-Video-34B-DPO"}. This record does not assert independent reproduction. ### MiniGPT-4V+ F1 Score: 23.6. Result ID: 69937e533a6c3148491656c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"MiniGPT-4V-Mistral"}. This record does not assert independent reproduction. ### Video-LLaVA F1 Score: 19.4. Result ID: 69937e533a6c3148491656c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Video-LLaVA"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.