# Video Question Answering on M3IT ActivNetQA Source: [Video Question Answering on M3IT ActivNetQA]() Collection index: [llms.txt]() Data updated: 2026-03-04T13:13:05.544Z Evaluation of model performance on the M3IT ActivNetQA dataset for Video Question Answering tasks, reporting Rouge-L scores. 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) | M3IT ActivNetQA | | Metric | Rouge-L | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [Rouge-L](): Higher is better; unit: PERCENT. ## Recorded results | Method | Rouge-L | Result date | Report paper | | --- | --- | --- | --- | | v-LCM | 63.6 | Not recorded | 69a66c142d603e6de3e3cda5 | | Qwen2-VL | 53.7 | Not recorded | 69a66c142d603e6de3e3cda5 | | Qwen2.5-VL | 52.1 | Not recorded | 69a66c142d603e6de3e3cda5 | | LCM | 51.7 | Not recorded | 69a66c142d603e6de3e3cda5 | | Qwen2.5-VL | 46 | Not recorded | 69a66c142d603e6de3e3cda5 | | Qwen2-VL | 41.9 | Not recorded | 69a66c142d603e6de3e3cda5 | | InterVL2 | 40.6 | Not recorded | 69a66c142d603e6de3e3cda5 | | Percep. LM | 40.5 | Not recorded | 69a66c142d603e6de3e3cda5 | | InterVL2 | 29.7 | Not recorded | 69a66c142d603e6de3e3cda5 | | Percep. LM | 28 | Not recorded | 69a66c142d603e6de3e3cda5 | | Percep. LM | 27.8 | Not recorded | 69a66c142d603e6de3e3cda5 | | InterVL2 | 27.5 | Not recorded | 69a66c142d603e6de3e3cda5 | | InternVL-2.5 | 26.8 | Not recorded | 69a66c142d603e6de3e3cda5 | | InternVL-2.5 | 20.9 | Not recorded | 69a66c142d603e6de3e3cda5 | | InternVL-2.5 | 16.6 | Not recorded | 69a66c142d603e6de3e3cda5 | ### v-LCM Rouge-L: 63.6. Result ID: 69a82fc96dbb7075b94e95d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"v-LCM"}. This record does not assert independent reproduction. ### Qwen2-VL Rouge-L: 53.7. Result ID: 69a82fc96dbb7075b94e95cc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"2B"}. This record does not assert independent reproduction. ### Qwen2.5-VL Rouge-L: 52.1. Result ID: 69a82fc96dbb7075b94e95ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B"}. This record does not assert independent reproduction. ### LCM Rouge-L: 51.7. Result ID: 69a82fc96dbb7075b94e95d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"LCM"}. This record does not assert independent reproduction. ### Qwen2.5-VL Rouge-L: 46. Result ID: 69a82fc96dbb7075b94e95cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### Qwen2-VL Rouge-L: 41.9. Result ID: 69a82fc96dbb7075b94e95cd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### InterVL2 Rouge-L: 40.6. Result ID: 69a82fc96dbb7075b94e95c6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"1B"}. This record does not assert independent reproduction. ### Percep. LM Rouge-L: 40.5. Result ID: 69a82fc96dbb7075b94e95d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"8B"}. This record does not assert independent reproduction. ### InterVL2 Rouge-L: 29.7. Result ID: 69a82fc96dbb7075b94e95c8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"8B"}. This record does not assert independent reproduction. ### Percep. LM Rouge-L: 28. Result ID: 69a82fc96dbb7075b94e95d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B"}. This record does not assert independent reproduction. ### Percep. LM Rouge-L: 27.8. Result ID: 69a82fc96dbb7075b94e95d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"1B"}. This record does not assert independent reproduction. ### InterVL2 Rouge-L: 27.5. Result ID: 69a82fc96dbb7075b94e95c7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"4B"}. This record does not assert independent reproduction. ### InternVL-2.5 Rouge-L: 26.8. Result ID: 69a82fc96dbb7075b94e95ca. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"4B"}. This record does not assert independent reproduction. ### InternVL-2.5 Rouge-L: 20.9. Result ID: 69a82fc96dbb7075b94e95cb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"8B"}. This record does not assert independent reproduction. ### InternVL-2.5 Rouge-L: 16.6. Result ID: 69a82fc96dbb7075b94e95c9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"1B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.