# Event-based Video Question Answering on EvQA 1000 Questions (full) Source: [Event-based Video Question Answering on EvQA 1000 Questions (full)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:31:53.742Z Evaluation of model performance on the full set of 1000 questions for the EvQA dataset, focusing on event-based video question answering. 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 | Event-based Video Question Answering | | Dataset (including any stated split) | EvQA 1000 Questions (full) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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. - [Tokens](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | FRT | 76.1 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 73.9 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 73 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 72 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 69.4 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 69.2 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 68.7 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 67.8 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 67.7 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 67.3 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 66.1 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 65.6 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 64.9 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 63.8 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 63.2 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 62.1 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 61.9 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 61.5 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 60.3 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 58.8 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 58.3 | Not recorded | 693f95ea6cfd488761a818ba | | ART | 57.9 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 56.8 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 56.6 | Not recorded | 693f95ea6cfd488761a818ba | | FRT | 55.1 | Not recorded | 693f95ea6cfd488761a818ba | | ART | 50.9 | Not recorded | 693f95ea6cfd488761a818ba | | ART | 49.3 | Not recorded | 693f95ea6cfd488761a818ba | | ART | 46.3 | Not recorded | 693f95ea6cfd488761a818ba | ### FRT Accuracy: 76.1. Result ID: 699854bc5698665ec4b2a392. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"24","Model Size":"32B"}. This record does not assert independent reproduction. ### FRT Accuracy: 73.9. Result ID: 699854bc5698665ec4b2a38e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"8","Model Size":"32B"}. This record does not assert independent reproduction. ### FRT Accuracy: 73. Result ID: 699854bc5698665ec4b2a38a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"4","Model Size":"32B"}. This record does not assert independent reproduction. ### FRT Accuracy: 72. Result ID: 699854bc5698665ec4b2a391. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"24","Model Size":"8B"}. This record does not assert independent reproduction. ### FRT Accuracy: 69.4. Result ID: 699854bc5698665ec4b2a38d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"8","Model Size":"8B"}. This record does not assert independent reproduction. ### FRT Accuracy: 69.2. Result ID: 699854bc5698665ec4b2a390. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"24","Model Size":"4B"}. This record does not assert independent reproduction. ### FRT Accuracy: 68.7. Result ID: 699854bc5698665ec4b2a386. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"2","Model Size":"32B"}. This record does not assert independent reproduction. ### FRT Accuracy: 67.8. Result ID: 699854bc5698665ec4b2a389. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"4","Model Size":"8B"}. This record does not assert independent reproduction. ### FRT Accuracy: 67.7. Result ID: 699854bc5698665ec4b2a38c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"8","Model Size":"4B"}. This record does not assert independent reproduction. ### FRT Accuracy: 67.3. Result ID: 699854bc5698665ec4b2a38f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"24","Model Size":"2B"}. This record does not assert independent reproduction. ### FRT Accuracy: 66.1. Result ID: 699854bc5698665ec4b2a382. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"1","Model Size":"32B"}. This record does not assert independent reproduction. ### FRT Accuracy: 65.6. Result ID: 699854bc5698665ec4b2a385. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"2","Model Size":"8B"}. This record does not assert independent reproduction. ### FRT Accuracy: 64.9. Result ID: 699854bc5698665ec4b2a388. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"4","Model Size":"4B"}. This record does not assert independent reproduction. ### FRT Accuracy: 63.8. Result ID: 699854bc5698665ec4b2a38b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"8","Model Size":"2B"}. This record does not assert independent reproduction. ### FRT Accuracy: 63.2. Result ID: 699854bc5698665ec4b2a37e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"0.1","Model Size":"32B"}. This record does not assert independent reproduction. ### FRT Accuracy: 62.1. Result ID: 699854bc5698665ec4b2a384. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"2","Model Size":"4B"}. This record does not assert independent reproduction. ### FRT Accuracy: 61.9. Result ID: 699854bc5698665ec4b2a387. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"4","Model Size":"2B"}. This record does not assert independent reproduction. ### FRT Accuracy: 61.5. Result ID: 699854bc5698665ec4b2a381. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"1","Model Size":"8B"}. This record does not assert independent reproduction. ### FRT Accuracy: 60.3. Result ID: 699854bc5698665ec4b2a383. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"2","Model Size":"2B"}. This record does not assert independent reproduction. ### FRT Accuracy: 58.8. Result ID: 699854bc5698665ec4b2a37d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"0.1","Model Size":"8B"}. This record does not assert independent reproduction. ### FRT Accuracy: 58.3. Result ID: 699854bc5698665ec4b2a380. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"1","Model Size":"4B"}. This record does not assert independent reproduction. ### ART Accuracy: 57.9. Result ID: 699854bc5698665ec4b2a396. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":null,"Model Size":"32B"}. This record does not assert independent reproduction. ### FRT Accuracy: 56.8. Result ID: 699854bc5698665ec4b2a37f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"1","Model Size":"2B"}. This record does not assert independent reproduction. ### FRT Accuracy: 56.6. Result ID: 699854bc5698665ec4b2a37c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"0.1","Model Size":"4B"}. This record does not assert independent reproduction. ### FRT Accuracy: 55.1. Result ID: 699854bc5698665ec4b2a37b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":"0.1","Model Size":"2B"}. This record does not assert independent reproduction. ### ART Accuracy: 50.9. Result ID: 699854bc5698665ec4b2a395. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":null,"Model Size":"8B"}. This record does not assert independent reproduction. ### ART Accuracy: 49.3. Result ID: 699854bc5698665ec4b2a394. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":null,"Model Size":"4B"}. This record does not assert independent reproduction. ### ART Accuracy: 46.3. Result ID: 699854bc5698665ec4b2a393. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"FPS":null,"Model Size":"2B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.