# Future Video Question Answering on FutureVQA Source: [Future Video Question Answering on FutureVQA]() Collection index: [llms.txt]() Data updated: 2026-03-11T08:58:57.208Z Evaluation of model performance on the FutureVQA dataset for Future Video Question Answering, reporting temporal accuracy metrics (Acc@1s, Acc@4s, Acc@12s) and ranking metrics (NDR, mRAR). 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 | Future Video Question Answering | | Dataset (including any stated split) | FutureVQA | | Metric | Acc@1s | | 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 - [Acc@1s](): Higher is better; unit: PERCENT. - [Acc@4s](): Higher is better; unit: PERCENT. - [Acc@12s](): Higher is better; unit: PERCENT. - [Delta Accuracy (1s to 12s)](): Higher is better; unit: PERCENT. - [mAcc (1-12s)](): Higher is better; unit: PERCENT. - [NDR](): Higher is better; unit: SCALAR. - [mRAR](): Higher is better; unit: SCALAR. ## Recorded results | Method | Acc@1s | Result date | Report paper | | --- | --- | --- | --- | | Qwen2.5-VL-7b | 61.9 | Not recorded | 69b0f72d2d603e6de3e45f8d | | FutureAgent | 60.8 | Not recorded | 69b0f72d2d603e6de3e45f8d | | FutureAgent | 60.5 | Not recorded | 69b0f72d2d603e6de3e45f8d | | Baseline | 60.2 | Not recorded | 69b0f72d2d603e6de3e45f8d | | GPT-4o | 59.1 | Not recorded | 69b0f72d2d603e6de3e45f8d | | LLV-Video | 53.7 | Not recorded | 69b0f72d2d603e6de3e45f8d | | Vid-LMA2 | 52.4 | Not recorded | 69b0f72d2d603e6de3e45f8d | | Baseline | 49.8 | Not recorded | 69b0f72d2d603e6de3e45f8d | | FutureAgent | 49.2 | Not recorded | 69b0f72d2d603e6de3e45f8d | | GPT-4o-mini | 47.7 | Not recorded | 69b0f72d2d603e6de3e45f8d | | Yi-VL-34b | 38.1 | Not recorded | 69b0f72d2d603e6de3e45f8d | | LLV-v1.5-13b | 37.8 | Not recorded | 69b0f72d2d603e6de3e45f8d | | LLV-v1.5-7b | 24 | Not recorded | 69b0f72d2d603e6de3e45f8d | | CogVLM-17b | 22.8 | Not recorded | 69b0f72d2d603e6de3e45f8d | | LLV-Next-13b | 15.4 | Not recorded | 69b0f72d2d603e6de3e45f8d | ### Qwen2.5-VL-7b Acc@1s: 61.9. Result ID: 69b12ecb6dbb7075b95bbafe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FutureAgent Acc@1s: 60.8. Result ID: 69b12ecb6dbb7075b95bbb05. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"temporal label training":true}. This record does not assert independent reproduction. ### FutureAgent Acc@1s: 60.5. Result ID: 69b12ecb6dbb7075b95bbb06. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"temporal label training":true,"Chain of Thought":false}. This record does not assert independent reproduction. ### Baseline Acc@1s: 60.2. Result ID: 69b12ecb6dbb7075b95bbb04. [Reporting paper]() Recorded evaluation configuration: {"temporal label training":true}. This record does not assert independent reproduction. ### GPT-4o Acc@1s: 59.1. Result ID: 69b12ecb6dbb7075b95bbaf8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLV-Video Acc@1s: 53.7. Result ID: 69b12ecb6dbb7075b95bbafd. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Vid-LMA2 Acc@1s: 52.4. Result ID: 69b12ecb6dbb7075b95bbb01. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Baseline Acc@1s: 49.8. Result ID: 69b12ecb6dbb7075b95bbb02. [Reporting paper]() Recorded evaluation configuration: {"temporal label training":false}. This record does not assert independent reproduction. ### FutureAgent Acc@1s: 49.2. Result ID: 69b12ecb6dbb7075b95bbb03. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"temporal label training":false}. This record does not assert independent reproduction. ### GPT-4o-mini Acc@1s: 47.7. Result ID: 69b12ecb6dbb7075b95bbaf9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Yi-VL-34b Acc@1s: 38.1. Result ID: 69b12ecb6dbb7075b95bbb00. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLV-v1.5-13b Acc@1s: 37.8. Result ID: 69b12ecb6dbb7075b95bbafb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLV-v1.5-7b Acc@1s: 24. Result ID: 69b12ecb6dbb7075b95bbafa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CogVLM-17b Acc@1s: 22.8. Result ID: 69b12ecb6dbb7075b95bbaff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLV-Next-13b Acc@1s: 15.4. Result ID: 69b12ecb6dbb7075b95bbafc. [Reporting 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.