# Video Question Answering on Video-MME w.o. sub. Medium Source: [Video Question Answering on Video-MME w.o. sub. Medium]() Collection index: [llms.txt]() Data updated: 2026-07-03T07:10:42.873Z Evaluation of model performance on the Video-MME dataset variant excluding subtitles ('w.o. sub.') and restricted to the Medium subset, for Video Question Answering, reporting 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) | Video-MME w.o. sub. Medium | | Metric | Accuracy | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen2-VL + ReQuest | 70.8 | Not recorded | 6a47420b143ebdcacacc5c6e | | Qwen2-VL | 70.1 | Not recorded | 6a47420b143ebdcacacc5c6e | | LLaVA-Video + ReQuest | 64.1 | Not recorded | 6a47420b143ebdcacacc5c6e | | NVILA | 62.2 | Not recorded | 6a47420b143ebdcacacc5c6e | | VideoTree | 59.9 | Not recorded | 6a47420b143ebdcacacc5c6e | | LLaVA-Video | 59.3 | Not recorded | 6a47420b143ebdcacacc5c6e | | LLaVa-OneVision + ReQuest | 58.8 | Not recorded | 6a47420b143ebdcacacc5c6e | | LongVU | 58.2 | Not recorded | 6a47420b143ebdcacacc5c6e | | LLaVa-OneVision | 56.6 | Not recorded | 6a47420b143ebdcacacc5c6e | | Frame-Voyager | 56.3 | Not recorded | 6a47420b143ebdcacacc5c6e | | LLoVi | 53.2 | Not recorded | 6a47420b143ebdcacacc5c6e | | VideoLLaMA2 | 45.4 | Not recorded | 6a47420b143ebdcacacc5c6e | | Chat-UniVi-V1.5 | 40.3 | Not recorded | 6a47420b143ebdcacacc5c6e | | Video-LLaVA | 38 | Not recorded | 6a47420b143ebdcacacc5c6e | | VideoChat2 | 37 | Not recorded | 6a47420b143ebdcacacc5c6e | | ShareGPT4Video | 36.3 | Not recorded | 6a47420b143ebdcacacc5c6e | ### Qwen2-VL + ReQuest Accuracy: 70.8. Result ID: 6a47607160b88bb339928658. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Size":"8B","#Frames":"≤ 512","zero-shot transfer":"true"}. This record does not assert independent reproduction. ### Qwen2-VL Accuracy: 70.1. Result ID: 6a47607160b88bb339928657. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Size":"8B","#Frames":"512","reproduced":"true"}. This record does not assert independent reproduction. ### LLaVA-Video + ReQuest Accuracy: 64.1. Result ID: 6a47607160b88bb339928654. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Size":"7B","#Frames":"32"}. This record does not assert independent reproduction. ### NVILA Accuracy: 62.2. Result ID: 6a47607160b88bb339928650. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Size":"8B","#Frames":"1024"}. This record does not assert independent reproduction. ### VideoTree Accuracy: 59.9. Result ID: 6a47607160b88bb339928652. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM Size":"–","#Frames":"–"}. This record does not assert independent reproduction. ### LLaVA-Video Accuracy: 59.3. Result ID: 6a47607160b88bb339928653. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM Size":"7B","#Frames":"32","reproduced":"true"}. This record does not assert independent reproduction. ### LLaVa-OneVision + ReQuest Accuracy: 58.8. Result ID: 6a47607160b88bb339928656. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Size":"7B","#Frames":"32","zero-shot transfer":"true"}. This record does not assert independent reproduction. ### LongVU Accuracy: 58.2. Result ID: 6a47607160b88bb33992864f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM Size":"7B","#Frames":"1fps"}. This record does not assert independent reproduction. ### LLaVa-OneVision Accuracy: 56.6. Result ID: 6a47607160b88bb339928655. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM Size":"7B","#Frames":"32","reproduced":"true"}. This record does not assert independent reproduction. ### Frame-Voyager Accuracy: 56.3. Result ID: 6a47607160b88bb33992864e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Size":"7B","#Frames":"8"}. This record does not assert independent reproduction. ### LLoVi Accuracy: 53.2. Result ID: 6a47607160b88bb339928651. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM Size":"–","#Frames":"–"}. This record does not assert independent reproduction. ### VideoLLaMA2 Accuracy: 45.4. Result ID: 6a47607160b88bb33992864d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM Size":"7B","#Frames":"16"}. This record does not assert independent reproduction. ### Chat-UniVi-V1.5 Accuracy: 40.3. Result ID: 6a47607160b88bb33992864c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM Size":"7B","#Frames":"64"}. This record does not assert independent reproduction. ### Video-LLaVA Accuracy: 38. Result ID: 6a47607160b88bb339928649. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM Size":"7B","#Frames":"8"}. This record does not assert independent reproduction. ### VideoChat2 Accuracy: 37. Result ID: 6a47607160b88bb33992864a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Size":"7B","#Frames":"16"}. This record does not assert independent reproduction. ### ShareGPT4Video Accuracy: 36.3. Result ID: 6a47607160b88bb33992864b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM Size":"8B","#Frames":"16"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.