# Video Question Answering on UrbanVideo-Bench Source: [Video Question Answering on UrbanVideo-Bench]() Collection index: [llms.txt]() Data updated: 2026-03-04T21:13:01.321Z Evaluation of model performance on the UrbanVideo-Bench dataset for Video Question Answering capabilities. 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) | UrbanVideo-Bench | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 | | --- | --- | --- | --- | | ACE-Brain-0-8B | 56.9 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Qwen-VL-Max | 45.5 | Not recorded | 69a7bc892d603e6de3e3d5bf | | GPT-4o | 43.6 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Qwen3-VL-8B-Inst. | 39.2 | Not recorded | 69a7bc892d603e6de3e3d5bf | | RoboBrain2.5-8B | 37.5 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Pelican-VL-7B | 37.1 | Not recorded | 69a7bc892d603e6de3e3d5bf | | VeBrain-7B | 36.5 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Qwen2.5-VL-7B-Inst. | 34.6 | Not recorded | 69a7bc892d603e6de3e3d5bf | | InternVL3.5-8B | 34.6 | Not recorded | 69a7bc892d603e6de3e3d5bf | | InternVL3-8B | 30.8 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Qwen3-VL-2B-Inst. | 30.5 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Vlaser-8B | 30.4 | Not recorded | 69a7bc892d603e6de3e3d5bf | | RoboBrain2.0-7B | 30 | Not recorded | 69a7bc892d603e6de3e3d5bf | | MiMo-Embodied-7B | 26 | Not recorded | 69a7bc892d603e6de3e3d5bf | ### ACE-Brain-0-8B Accuracy: 56.9. Result ID: 69a8a0566dbb7075b9519643. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Embodied Brain MLLMs"}. This record does not assert independent reproduction. ### Qwen-VL-Max Accuracy: 45.5. Result ID: 69a8a0566dbb7075b9519637. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Closed-source MLLMs"}. This record does not assert independent reproduction. ### GPT-4o Accuracy: 43.6. Result ID: 69a8a0566dbb7075b9519636. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Closed-source MLLMs"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Inst. Accuracy: 39.2. Result ID: 69a8a0566dbb7075b951963c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source general-purpose MLLMs"}. This record does not assert independent reproduction. ### RoboBrain2.5-8B Accuracy: 37.5. Result ID: 69a8a0566dbb7075b951963e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Embodied Brain MLLMs"}. This record does not assert independent reproduction. ### Pelican-VL-7B Accuracy: 37.1. Result ID: 69a8a0566dbb7075b9519640. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Embodied Brain MLLMs"}. This record does not assert independent reproduction. ### VeBrain-7B Accuracy: 36.5. Result ID: 69a8a0566dbb7075b951963f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Embodied Brain MLLMs"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Inst. Accuracy: 34.6. Result ID: 69a8a0566dbb7075b9519638. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source general-purpose MLLMs"}. This record does not assert independent reproduction. ### InternVL3.5-8B Accuracy: 34.6. Result ID: 69a8a0566dbb7075b951963a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source general-purpose MLLMs"}. This record does not assert independent reproduction. ### InternVL3-8B Accuracy: 30.8. Result ID: 69a8a0566dbb7075b9519639. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source general-purpose MLLMs"}. This record does not assert independent reproduction. ### Qwen3-VL-2B-Inst. Accuracy: 30.5. Result ID: 69a8a0566dbb7075b951963b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source general-purpose MLLMs"}. This record does not assert independent reproduction. ### Vlaser-8B Accuracy: 30.4. Result ID: 69a8a0566dbb7075b9519642. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Embodied Brain MLLMs"}. This record does not assert independent reproduction. ### RoboBrain2.0-7B Accuracy: 30. Result ID: 69a8a0566dbb7075b951963d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Embodied Brain MLLMs"}. This record does not assert independent reproduction. ### MiMo-Embodied-7B Accuracy: 26. Result ID: 69a8a0566dbb7075b9519641. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Embodied Brain MLLMs"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.