# Video Question Answering on ActivityNet-200 Fine-grained 1.0 (test) Source: [Video Question Answering on ActivityNet-200 Fine-grained 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:39:53.814Z Evaluation of Video Question Answering performance on the test split of the ActivityNet-200 Fine-grained 1.0 dataset, using multi-faceted correctness metrics. 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) | ActivityNet-200 Fine-grained 1.0 (test) | | Metric | Correctness | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [Correctness](): Higher is better; unit: SCALAR. - [Detail Score](): Higher is better; unit: SCALAR. - [Context Score](): Higher is better; unit: SCALAR. - [Temporal Score](): Higher is better; unit: SCALAR. - [Consistency Score](): Higher is better; unit: SCALAR. - [Average Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Correctness | Result date | Report paper | | --- | --- | --- | --- | | ST-LLM | 3.23 | Not recorded | 68fa77a51e209131cea74967 | | VideoChat2 | 3.02 | Not recorded | 68fa77a51e209131cea74967 | | LLAMA-VID | 2.96 | Not recorded | 68fa77a51e209131cea74967 | | ChatUniVi | 2.89 | Not recorded | 68fa77a51e209131cea74967 | | Video-LLaVA | 2.84 | Not recorded | 68fa77a51e209131cea74967 | | Video-Panda | 2.74 | Not recorded | 68fa77a51e209131cea74967 | | Video-LLaVA\* | 2.46 | Not recorded | 68fa77a51e209131cea74967 | | Video-ChatGPT | 2.4 | Not recorded | 68fa77a51e209131cea74967 | | VideoChat | 2.23 | Not recorded | 68fa77a51e209131cea74967 | | LLAMA Adapter | 2.03 | Not recorded | 68fa77a51e209131cea74967 | | Video-LLaMA | 1.96 | Not recorded | 68fa77a51e209131cea74967 | ### ST-LLM Correctness: 3.23. Result ID: 69955b5a3badfaffe64cc96e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Encoder-based","Training Data Scope":"Different Datasets","Vision Size":"1.3B","Modality":"V"}. This record does not assert independent reproduction. ### VideoChat2 Correctness: 3.02. Result ID: 69955b5a3badfaffe64cc96d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"Encoder-based","Training Data Scope":"Different Datasets","Vision Size":"496M","Modality":"V+I"}. This record does not assert independent reproduction. ### LLAMA-VID Correctness: 2.96. Result ID: 69955b5a3badfaffe64cc96b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Encoder-based","Training Data Scope":"Different Datasets","Vision Size":"1B","Modality":"V+I"}. This record does not assert independent reproduction. ### ChatUniVi Correctness: 2.89. Result ID: 69955b5a3badfaffe64cc96a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Encoder-based","Training Data Scope":"Different Datasets","Vision Size":"307M","Modality":"V+I"}. This record does not assert independent reproduction. ### Video-LLaVA Correctness: 2.84. Result ID: 69955b5a3badfaffe64cc96c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Encoder-based","Training Data Scope":"Different Datasets","Vision Size":"425M","Modality":"V+I"}. This record does not assert independent reproduction. ### Video-Panda Correctness: 2.74. Result ID: 69955b5a3badfaffe64cc971. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Encoder-free","Training Data Scope":"Same Dataset","Vision Size":"45M","Modality":"V"}. This record does not assert independent reproduction. ### Video-LLaVA\* Correctness: 2.46. Result ID: 69955b5a3badfaffe64cc970. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Encoder-based","Training Data Scope":"Same Dataset","Vision Size":"425M","Modality":"V","Note":"trained with video-only datasets for fair comparison"}. This record does not assert independent reproduction. ### Video-ChatGPT Correctness: 2.4. Result ID: 69955b5a3badfaffe64cc96f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Encoder-based","Training Data Scope":"Same Dataset","Vision Size":"307M","Modality":"V"}. This record does not assert independent reproduction. ### VideoChat Correctness: 2.23. Result ID: 69955b5a3badfaffe64cc967. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"Encoder-based","Training Data Scope":"Different Datasets","Vision Size":"1.2B","Modality":"V"}. This record does not assert independent reproduction. ### LLAMA Adapter Correctness: 2.03. Result ID: 69955b5a3badfaffe64cc968. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Encoder-based","Training Data Scope":"Different Datasets","Vision Size":"404.3M","Modality":"I"}. This record does not assert independent reproduction. ### Video-LLaMA Correctness: 1.96. Result ID: 69955b5a3badfaffe64cc969. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Encoder-based","Training Data Scope":"Different Datasets","Vision Size":"1.1B","Modality":"V"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.