# Video Question Answering on LVBench (test) Source: [Video Question Answering on LVBench (test)]() Collection index: [llms.txt]() Data updated: 2026-04-08T07:47:16.313Z Evaluation of model performance on the test split of the LVBench dataset for Video Question Answering, measured using 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) | LVBench (test) | | 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 | | --- | --- | --- | --- | | GPT-4o | 48.9 | Not recorded | 69d5e1237d0172140ec75b34 | | InternVL 2.5 | 43.6 | Not recorded | 69d5e1237d0172140ec75b34 | | VideoMind | 40.8 | Not recorded | 69d5e1237d0172140ec75b34 | | SVAgent | 40.8 | Not recorded | 69d5e1237d0172140ec75b34 | | SVAgent | 40.6 | Not recorded | 69d5e1237d0172140ec75b34 | | Qwen2.5-VL | 39.3 | Not recorded | 69d5e1237d0172140ec75b34 | | LLaVA-Video | 38.7 | Not recorded | 69d5e1237d0172140ec75b34 | | SVAgent | 38.5 | Not recorded | 69d5e1237d0172140ec75b34 | | SVAgent | 37.6 | Not recorded | 69d5e1237d0172140ec75b34 | | Qwen2.5-VL | 33.9 | Not recorded | 69d5e1237d0172140ec75b34 | | Qwen3-VL | 33.4 | Not recorded | 69d5e1237d0172140ec75b34 | | Gemini 1.5 Pro | 33.1 | Not recorded | 69d5e1237d0172140ec75b34 | | Qwen3-VL | 32.1 | Not recorded | 69d5e1237d0172140ec75b34 | | Qwen2.5-VL | 31.6 | Not recorded | 69d5e1237d0172140ec75b34 | ### GPT-4o Accuracy: 48.9. Result ID: 69d607fb47f34ce924be50bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"-","# Frames":"1fps"}. This record does not assert independent reproduction. ### InternVL 2.5 Accuracy: 43.6. Result ID: 69d607fb47f34ce924be50c2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"78B","# Frames":"64"}. This record does not assert independent reproduction. ### VideoMind Accuracy: 40.8. Result ID: 69d607fb47f34ce924be50c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B","# Frames":"32"}. This record does not assert independent reproduction. ### SVAgent Accuracy: 40.8. Result ID: 69d607fb47f34ce924be50cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL","Size":"8B","# Frames":"8"}. This record does not assert independent reproduction. ### SVAgent Accuracy: 40.6. Result ID: 69d607fb47f34ce924be50c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Size":"7B","# Frames":"8"}. This record does not assert independent reproduction. ### Qwen2.5-VL Accuracy: 39.3. Result ID: 69d607fb47f34ce924be50c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"72B","# Frames":"32 / 768∗"}. This record does not assert independent reproduction. ### LLaVA-Video Accuracy: 38.7. Result ID: 69d607fb47f34ce924be50c0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"72B","# Frames":"32 / 64∗"}. This record does not assert independent reproduction. ### SVAgent Accuracy: 38.5. Result ID: 69d607fb47f34ce924be50c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Size":"3B","# Frames":"8"}. This record does not assert independent reproduction. ### SVAgent Accuracy: 37.6. Result ID: 69d607fb47f34ce924be50c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL","Size":"4B","# Frames":"8"}. This record does not assert independent reproduction. ### Qwen2.5-VL Accuracy: 33.9. Result ID: 69d607fb47f34ce924be50c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B","# Frames":"8"}. This record does not assert independent reproduction. ### Qwen3-VL Accuracy: 33.4. Result ID: 69d607fb47f34ce924be50ca. [Reporting paper]() Recorded evaluation configuration: {"Size":"8B","# Frames":"8"}. This record does not assert independent reproduction. ### Gemini 1.5 Pro Accuracy: 33.1. Result ID: 69d607fb47f34ce924be50be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"-","# Frames":"1fps"}. This record does not assert independent reproduction. ### Qwen3-VL Accuracy: 32.1. Result ID: 69d607fb47f34ce924be50c6. [Reporting paper]() Recorded evaluation configuration: {"Size":"4B","# Frames":"8"}. This record does not assert independent reproduction. ### Qwen2.5-VL Accuracy: 31.6. Result ID: 69d607fb47f34ce924be50c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"3B","# Frames":"8"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.