# Video Question Answering on M3IT MSRVTT-QA Source: [Video Question Answering on M3IT MSRVTT-QA]() Collection index: [llms.txt]() Data updated: 2026-03-04T13:13:05.573Z Evaluation of model performance on the M3IT MSRVTT-QA dataset for Video Question Answering, 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 MSRVTT-QA | | 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 | 48.7 | Not recorded | 69a66c142d603e6de3e3cda5 | | Qwen2.5-VL | 41.6 | Not recorded | 69a66c142d603e6de3e3cda5 | | Qwen2.5-VL | 41.4 | Not recorded | 69a66c142d603e6de3e3cda5 | | Qwen2-VL | 39.6 | Not recorded | 69a66c142d603e6de3e3cda5 | | LCM | 36 | Not recorded | 69a66c142d603e6de3e3cda5 | | InterVL2 | 27.6 | Not recorded | 69a66c142d603e6de3e3cda5 | | InterVL2 | 27.1 | Not recorded | 69a66c142d603e6de3e3cda5 | | Percep. LM | 25.3 | Not recorded | 69a66c142d603e6de3e3cda5 | | InterVL2 | 24.5 | Not recorded | 69a66c142d603e6de3e3cda5 | | Qwen2-VL | 22.7 | Not recorded | 69a66c142d603e6de3e3cda5 | | InternVL-2.5 | 21.8 | Not recorded | 69a66c142d603e6de3e3cda5 | | Percep. LM | 19.4 | Not recorded | 69a66c142d603e6de3e3cda5 | | InternVL-2.5 | 16.9 | Not recorded | 69a66c142d603e6de3e3cda5 | | Percep. LM | 14.5 | Not recorded | 69a66c142d603e6de3e3cda5 | | InternVL-2.5 | 11.7 | Not recorded | 69a66c142d603e6de3e3cda5 | ### v-LCM ROUGE-L: 48.7. Result ID: 69a82fc96dbb7075b94e95e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"v-LCM"}. This record does not assert independent reproduction. ### Qwen2.5-VL ROUGE-L: 41.6. Result ID: 69a82fc96dbb7075b94e95dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B"}. This record does not assert independent reproduction. ### Qwen2.5-VL ROUGE-L: 41.4. Result ID: 69a82fc96dbb7075b94e95de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### Qwen2-VL ROUGE-L: 39.6. Result ID: 69a82fc96dbb7075b94e95db. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"2B"}. This record does not assert independent reproduction. ### LCM ROUGE-L: 36. Result ID: 69a82fc96dbb7075b94e95e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"LCM"}. This record does not assert independent reproduction. ### InterVL2 ROUGE-L: 27.6. Result ID: 69a82fc96dbb7075b94e95d5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"1B"}. This record does not assert independent reproduction. ### InterVL2 ROUGE-L: 27.1. Result ID: 69a82fc96dbb7075b94e95d7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"8B"}. This record does not assert independent reproduction. ### Percep. LM ROUGE-L: 25.3. Result ID: 69a82fc96dbb7075b94e95e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"8B"}. This record does not assert independent reproduction. ### InterVL2 ROUGE-L: 24.5. Result ID: 69a82fc96dbb7075b94e95d6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"4B"}. This record does not assert independent reproduction. ### Qwen2-VL ROUGE-L: 22.7. Result ID: 69a82fc96dbb7075b94e95dc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### InternVL-2.5 ROUGE-L: 21.8. Result ID: 69a82fc96dbb7075b94e95d9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"4B"}. This record does not assert independent reproduction. ### Percep. LM ROUGE-L: 19.4. Result ID: 69a82fc96dbb7075b94e95e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B"}. This record does not assert independent reproduction. ### InternVL-2.5 ROUGE-L: 16.9. Result ID: 69a82fc96dbb7075b94e95da. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"8B"}. This record does not assert independent reproduction. ### Percep. LM ROUGE-L: 14.5. Result ID: 69a82fc96dbb7075b94e95df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"1B"}. This record does not assert independent reproduction. ### InternVL-2.5 ROUGE-L: 11.7. Result ID: 69a82fc96dbb7075b94e95d8. [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.