# AI-generated video detection on Our Dataset HunyuanVideo Source: [AI-generated video detection on Our Dataset HunyuanVideo]() Collection index: [llms.txt]() Data updated: 2026-03-06T07:18:21.941Z Evaluation of model performance for detecting AI-generated videos using the Our Dataset HunyuanVideo dataset, reporting Top-1 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 | AI-generated video detection | | Dataset (including any stated split) | Our Dataset HunyuanVideo | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | VidGuard-R1 (GRPO-Q) | 86.17 | Not recorded | 68fa7be71e209131cea8b388 | | VidGuard-R1 (GRPO-TA) | 83.72 | Not recorded | 68fa7be71e209131cea8b388 | | VidGuard-R1 (GRPO) | 81.9 | Not recorded | 68fa7be71e209131cea8b388 | | VidGuard-R1 (DPO) | 80.88 | Not recorded | 68fa7be71e209131cea8b388 | | VideoSwin | 79.71 | Not recorded | 68fa7be71e209131cea8b388 | | SlowFast | 77.03 | Not recorded | 68fa7be71e209131cea8b388 | | TimeSformer | 74.55 | Not recorded | 68fa7be71e209131cea8b388 | | UniFormer V2 | 71.92 | Not recorded | 68fa7be71e209131cea8b388 | | TRN | 69.87 | Not recorded | 68fa7be71e209131cea8b388 | | VidGuard-R1 (CoT) | 63.19 | Not recorded | 68fa7be71e209131cea8b388 | | I3D | 62.13 | Not recorded | 68fa7be71e209131cea8b388 | | GPT-4o | 57.42 | Not recorded | 68fa7be71e209131cea8b388 | | Qwen2.5-VL-72B | 55.82 | Not recorded | 68fa7be71e209131cea8b388 | | GPT-4.1 mini | 55.31 | Not recorded | 68fa7be71e209131cea8b388 | | MViT V2 | 53.91 | Not recorded | 68fa7be71e209131cea8b388 | | Qwen2.5-VL-7B | 52.83 | Not recorded | 68fa7be71e209131cea8b388 | ### VidGuard-R1 (GRPO-Q) Top-1 Accuracy: 86.17. Result ID: 69aa7f306dbb7075b953d012. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"MLLM"}. This record does not assert independent reproduction. ### VidGuard-R1 (GRPO-TA) Top-1 Accuracy: 83.72. Result ID: 69aa7f306dbb7075b953d011. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"MLLM"}. This record does not assert independent reproduction. ### VidGuard-R1 (GRPO) Top-1 Accuracy: 81.9. Result ID: 69aa7f306dbb7075b953d010. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"MLLM"}. This record does not assert independent reproduction. ### VidGuard-R1 (DPO) Top-1 Accuracy: 80.88. Result ID: 69aa7f306dbb7075b953d00f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"MLLM"}. This record does not assert independent reproduction. ### VideoSwin Top-1 Accuracy: 79.71. Result ID: 69aa7f306dbb7075b953d008. [Reporting paper]() Recorded evaluation configuration: {"Type":"TF"}. This record does not assert independent reproduction. ### SlowFast Top-1 Accuracy: 77.03. Result ID: 69aa7f306dbb7075b953d003. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"CNN"}. This record does not assert independent reproduction. ### TimeSformer Top-1 Accuracy: 74.55. Result ID: 69aa7f306dbb7075b953d007. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"TF"}. This record does not assert independent reproduction. ### UniFormer V2 Top-1 Accuracy: 71.92. Result ID: 69aa7f306dbb7075b953d006. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"TF"}. This record does not assert independent reproduction. ### TRN Top-1 Accuracy: 69.87. Result ID: 69aa7f306dbb7075b953d005. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"CNN"}. This record does not assert independent reproduction. ### VidGuard-R1 (CoT) Top-1 Accuracy: 63.19. Result ID: 69aa7f306dbb7075b953d00e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"MLLM"}. This record does not assert independent reproduction. ### I3D Top-1 Accuracy: 62.13. Result ID: 69aa7f306dbb7075b953d004. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"CNN"}. This record does not assert independent reproduction. ### GPT-4o Top-1 Accuracy: 57.42. Result ID: 69aa7f306dbb7075b953d00d. [Reporting paper]() Recorded evaluation configuration: {"Type":"MLLM"}. This record does not assert independent reproduction. ### Qwen2.5-VL-72B Top-1 Accuracy: 55.82. Result ID: 69aa7f306dbb7075b953d00b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"MLLM"}. This record does not assert independent reproduction. ### GPT-4.1 mini Top-1 Accuracy: 55.31. Result ID: 69aa7f306dbb7075b953d00c. [Reporting paper]() Recorded evaluation configuration: {"Type":"MLLM"}. This record does not assert independent reproduction. ### MViT V2 Top-1 Accuracy: 53.91. Result ID: 69aa7f306dbb7075b953d009. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"TF"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Top-1 Accuracy: 52.83. Result ID: 69aa7f306dbb7075b953d00a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"MLLM"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.