# Video Question Answering on OVO-Bench Source: [Video Question Answering on OVO-Bench]() Collection index: [llms.txt]() Data updated: 2026-05-11T10:39:53.471Z Evaluation of model performance on the OVO-Bench dataset for Video Question Answering, reporting the Overall accuracy score. 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) | OVO-Bench | | Metric | Overall Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Overall Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Gemini 1.5 Pro | 65.93 | Not recorded | 6a0162c2dbc836b87d8233d0 | | Qwen2.5-VL-7B + SAVEMem | 62.69 | Not recorded | 6a0162c2dbc836b87d8233d0 | | GPT-4o | 62.6 | Not recorded | 6a0162c2dbc836b87d8233d0 | | ViSpeak | 61.91 | Not recorded | 6a0162c2dbc836b87d8233d0 | | ThinkStream | 59.66 | Not recorded | 6a0162c2dbc836b87d8233d0 | | Qwen2.5-VL-3B + SAVEMem | 57.34 | Not recorded | 6a0162c2dbc836b87d8233d0 | | StreamForest | 56.61 | Not recorded | 6a0162c2dbc836b87d8233d0 | | Qwen2-VL | 54.61 | Not recorded | 6a0162c2dbc836b87d8233d0 | | LLaVA-Video | 52.51 | Not recorded | 6a0162c2dbc836b87d8233d0 | | InternVL2 | 52.36 | Not recorded | 6a0162c2dbc836b87d8233d0 | | Qwen2.5-VL-7B | 52.27 | Not recorded | 6a0162c2dbc836b87d8233d0 | | Qwen2.5-VL-3B | 52.23 | Not recorded | 6a0162c2dbc836b87d8233d0 | | TimeChat-Online | 51.8 | Not recorded | 6a0162c2dbc836b87d8233d0 | | LongVU | 48.45 | Not recorded | 6a0162c2dbc836b87d8233d0 | | Dispider | 45.3 | Not recorded | 6a0162c2dbc836b87d8233d0 | | Flash-VStream | 27.61 | Not recorded | 6a0162c2dbc836b87d8233d0 | | VideoLLM-Online | 19.26 | Not recorded | 6a0162c2dbc836b87d8233d0 | ### Gemini 1.5 Pro Overall Accuracy: 65.93. Result ID: 6a01b08f47f34ce924e4438b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"-","Frames":"1 fps","Mode":"Proprietary"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B + SAVEMem Overall Accuracy: 62.69. Result ID: 6a01b08f47f34ce924e4439b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Free"}. This record does not assert independent reproduction. ### GPT-4o Overall Accuracy: 62.6. Result ID: 6a01b08f47f34ce924e4438c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"-","Frames":"64","Mode":"Proprietary"}. This record does not assert independent reproduction. ### ViSpeak Overall Accuracy: 61.91. Result ID: 6a01b08f47f34ce924e44394. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction. ### ThinkStream Overall Accuracy: 59.66. Result ID: 6a01b08f47f34ce924e44395. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"3B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B + SAVEMem Overall Accuracy: 57.34. Result ID: 6a01b08f47f34ce924e44399. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"3B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Free"}. This record does not assert independent reproduction. ### StreamForest Overall Accuracy: 56.61. Result ID: 6a01b08f47f34ce924e44397. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction. ### Qwen2-VL Overall Accuracy: 54.61. Result ID: 6a01b08f47f34ce924e4438e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B","Frames":"64","Mode":"Offline"}. This record does not assert independent reproduction. ### LLaVA-Video Overall Accuracy: 52.51. Result ID: 6a01b08f47f34ce924e4438d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B","Frames":"64","Mode":"Offline"}. This record does not assert independent reproduction. ### InternVL2 Overall Accuracy: 52.36. Result ID: 6a01b08f47f34ce924e4438f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"8B","Frames":"64","Mode":"Offline"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Overall Accuracy: 52.27. Result ID: 6a01b08f47f34ce924e4439a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Free"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Overall Accuracy: 52.23. Result ID: 6a01b08f47f34ce924e44398. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"3B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Free"}. This record does not assert independent reproduction. ### TimeChat-Online Overall Accuracy: 51.8. Result ID: 6a01b08f47f34ce924e44396. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction. ### LongVU Overall Accuracy: 48.45. Result ID: 6a01b08f47f34ce924e44390. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Offline"}. This record does not assert independent reproduction. ### Dispider Overall Accuracy: 45.3. Result ID: 6a01b08f47f34ce924e44392. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction. ### Flash-VStream Overall Accuracy: 27.61. Result ID: 6a01b08f47f34ce924e44393. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction. ### VideoLLM-Online Overall Accuracy: 19.26. Result ID: 6a01b08f47f34ce924e44391. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"8B","Frames":"2 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.