# Video Question Answering on VideoMME (Length and Subtitle Breakdown) Source: [Video Question Answering on VideoMME (Length and Subtitle Breakdown)]() Collection index: [llms.txt]() Data updated: 2026-04-08T07:47:16.343Z Evaluation of Video Question Answering performance on the VideoMME dataset, reporting accuracy metrics segmented by question length (Short, Medium, Long, Overall) and the presence of accompanying subtitles. 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) | VideoMME | | Metric | Accuracy (Overall, w/o Subtitles) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 (Overall, w/o Subtitles)](): Higher is better; unit: PERCENT. - [Accuracy (Short, w/o Subtitles)](): Higher is better; unit: PERCENT. - [Accuracy (Short, w/ Subtitles)](): Higher is better; unit: PERCENT. - [Accuracy (Medium, w/o Subtitles)](): Higher is better; unit: PERCENT. - [Accuracy (Medium, w/ Subtitles)](): Higher is better; unit: PERCENT. - [Accuracy (Long, w/o Subtitles)](): Higher is better; unit: PERCENT. - [Accuracy (Long, w/ Subtitles)](): Higher is better; unit: PERCENT. - [Accuracy (Overall, w/ Subtitles)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Overall, w/o Subtitles) | Result date | Report paper | | --- | --- | --- | --- | | Video-RAG | 77.4 | Not recorded | 69d5e1237d0172140ec75b34 | | Gemini 1.5 Pro | 75 | Not recorded | 69d5e1237d0172140ec75b34 | | Qwen2.5-VL | 74.1 | Not recorded | 69d5e1237d0172140ec75b34 | | InternVL 2.5 | 72.1 | Not recorded | 69d5e1237d0172140ec75b34 | | GPT-4o | 71.9 | Not recorded | 69d5e1237d0172140ec75b34 | | LLaVA-Video | 70.3 | Not recorded | 69d5e1237d0172140ec75b34 | | Vgent | 68.9 | Not recorded | 69d5e1237d0172140ec75b34 | | SVAgent | 63.1 | Not recorded | 69d5e1237d0172140ec75b34 | | SVAgent | 61.2 | Not recorded | 69d5e1237d0172140ec75b34 | | SVAgent | 60.7 | Not recorded | 69d5e1237d0172140ec75b34 | | SVAgent | 60.1 | Not recorded | 69d5e1237d0172140ec75b34 | | VideoMind | 58.2 | Not recorded | 69d5e1237d0172140ec75b34 | | Qwen3-VL | 55.8 | Not recorded | 69d5e1237d0172140ec75b34 | | Qwen3-VL | 53.9 | Not recorded | 69d5e1237d0172140ec75b34 | | Qwen2.5-VL | 52.8 | Not recorded | 69d5e1237d0172140ec75b34 | | Qwen2.5-VL | 52.8 | Not recorded | 69d5e1237d0172140ec75b34 | ### Video-RAG Accuracy (Overall, w/o Subtitles): 77.4. Result ID: 69d607fb47f34ce924be50d3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"72B","# Frames":"64"}. This record does not assert independent reproduction. ### Gemini 1.5 Pro Accuracy (Overall, w/o Subtitles): 75. Result ID: 69d607fb47f34ce924be50cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"-","# Frames":"1fps"}. This record does not assert independent reproduction. ### Qwen2.5-VL Accuracy (Overall, w/o Subtitles): 74.1. Result ID: 69d607fb47f34ce924be50cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"72B","# Frames":"32 / 768∗"}. This record does not assert independent reproduction. ### InternVL 2.5 Accuracy (Overall, w/o Subtitles): 72.1. Result ID: 69d607fb47f34ce924be50d0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"78B","# Frames":"64"}. This record does not assert independent reproduction. ### GPT-4o Accuracy (Overall, w/o Subtitles): 71.9. Result ID: 69d607fb47f34ce924be50cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"-","# Frames":"1fps"}. This record does not assert independent reproduction. ### LLaVA-Video Accuracy (Overall, w/o Subtitles): 70.3. Result ID: 69d607fb47f34ce924be50ce. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"72B","# Frames":"32 / 64∗"}. This record does not assert independent reproduction. ### Vgent Accuracy (Overall, w/o Subtitles): 68.9. Result ID: 69d607fb47f34ce924be50d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B","# Frames":"320"}. This record does not assert independent reproduction. ### SVAgent Accuracy (Overall, w/o Subtitles): 63.1. Result ID: 69d607fb47f34ce924be50db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL","Size":"8B","# Frames":"8"}. This record does not assert independent reproduction. ### SVAgent Accuracy (Overall, w/o Subtitles): 61.2. Result ID: 69d607fb47f34ce924be50d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Size":"7B","# Frames":"8"}. This record does not assert independent reproduction. ### SVAgent Accuracy (Overall, w/o Subtitles): 60.7. Result ID: 69d607fb47f34ce924be50d5. [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 (Overall, w/o Subtitles): 60.1. Result ID: 69d607fb47f34ce924be50d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL","Size":"4B","# Frames":"8"}. This record does not assert independent reproduction. ### VideoMind Accuracy (Overall, w/o Subtitles): 58.2. Result ID: 69d607fb47f34ce924be50d1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B","# Frames":"32"}. This record does not assert independent reproduction. ### Qwen3-VL Accuracy (Overall, w/o Subtitles): 55.8. Result ID: 69d607fb47f34ce924be50da. [Reporting paper]() Recorded evaluation configuration: {"Size":"8B","# Frames":"8"}. This record does not assert independent reproduction. ### Qwen3-VL Accuracy (Overall, w/o Subtitles): 53.9. Result ID: 69d607fb47f34ce924be50d6. [Reporting paper]() Recorded evaluation configuration: {"Size":"4B","# Frames":"8"}. This record does not assert independent reproduction. ### Qwen2.5-VL Accuracy (Overall, w/o Subtitles): 52.8. Result ID: 69d607fb47f34ce924be50d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"3B","# Frames":"8"}. This record does not assert independent reproduction. ### Qwen2.5-VL Accuracy (Overall, w/o Subtitles): 52.8. Result ID: 69d607fb47f34ce924be50d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B","# Frames":"8"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.