# Video Question Answering on MLVU long-form Source: [Video Question Answering on MLVU long-form]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:33:25.457Z Evaluation of model performance on the MLVU long-form 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) | MLVU long-form | | 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 | | --- | --- | --- | --- | | VideoChat-Flash-7B | 74.7 | Not recorded | 699e82116017c4460ffacf52 | | VideoLLaMA3-7B | 73 | Not recorded | 699e82116017c4460ffacf52 | | Oryx-1.5-32B | 72.3 | Not recorded | 699e82116017c4460ffacf52 | | LongVideo-R1 | 71.3 | Not recorded | 699e82116017c4460ffacf52 | | Aria-25B | 70.6 | Not recorded | 699e82116017c4460ffacf52 | | LinVT-7B | 68.9 | Not recorded | 699e82116017c4460ffacf52 | | LongVideo-R1 | 68.1 | Not recorded | 699e82116017c4460ffacf52 | | LLaVA-OV-72B | 66.4 | Not recorded | 699e82116017c4460ffacf52 | | Video-XL-7B | 64.9 | Not recorded | 699e82116017c4460ffacf52 | | GPT-4o | 64.6 | Not recorded | 699e82116017c4460ffacf52 | | VideoMind-7B | 64.4 | Not recorded | 699e82116017c4460ffacf52 | | Video-CCAM-14B | 63.1 | Not recorded | 699e82116017c4460ffacf52 | | VideoTree | 60.4 | Not recorded | 699e82116017c4460ffacf52 | | GPT-4V | 49.2 | Not recorded | 699e82116017c4460ffacf52 | ### VideoChat-Flash-7B Accuracy: 74.7. Result ID: 699ebbef5698665ec48b261e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VideoLLaMA3-7B Accuracy: 73. Result ID: 699ebbef5698665ec48b261d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Oryx-1.5-32B Accuracy: 72.3. Result ID: 699ebbef5698665ec48b261c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LongVideo-R1 Accuracy: 71.3. Result ID: 699ebbef5698665ec48b2622. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"updated\_version":true,"video\_captions":"Qwen3-VL-32B-Instruct","SFT\_data":"renewed"}. This record does not assert independent reproduction. ### Aria-25B Accuracy: 70.6. Result ID: 699ebbef5698665ec48b261b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LinVT-7B Accuracy: 68.9. Result ID: 699ebbef5698665ec48b261a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LongVideo-R1 Accuracy: 68.1. Result ID: 699ebbef5698665ec48b2621. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLaVA-OV-72B Accuracy: 66.4. Result ID: 699ebbef5698665ec48b2619. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Video-XL-7B Accuracy: 64.9. Result ID: 699ebbef5698665ec48b2618. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4o Accuracy: 64.6. Result ID: 699ebbef5698665ec48b2616. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VideoMind-7B Accuracy: 64.4. Result ID: 699ebbef5698665ec48b2620. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Video-CCAM-14B Accuracy: 63.1. Result ID: 699ebbef5698665ec48b2617. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VideoTree Accuracy: 60.4. Result ID: 699ebbef5698665ec48b261f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4V Accuracy: 49.2. Result ID: 699ebbef5698665ec48b2615. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.