# Deepfake Detection on OmniFake Full Suite Source: [Deepfake Detection on OmniFake Full Suite]() Collection index: [llms.txt]() Data updated: 2026-03-24T15:42:27.631Z Evaluation of Deepfake Detection performance across the entire OmniFake dataset suite, reporting overall 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 | Deepfake Detection | | Dataset (including any stated split) | OmniFake Full Suite | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 | | --- | --- | --- | --- | | VIGIL | 93.1 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | VIGIL Cold-Start | 89.8 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | DDA | 88.8 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | Veritas | 87.6 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | Co-SPY | 84.7 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | D^3 | 80.6 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | AIDE | 78.9 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | FakeVLM | 77.1 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | UnivFD | 76.6 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | Gemini-3-Pro | 75 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | NPR | 73.3 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | C2P-CLIP | 72.2 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | GPT-5.2 | 71.4 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | Kimi-K2.5 | 70.2 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | SAFE | 66.7 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | Qwen3-VL-8B | 59.4 | Not recorded | 69c21a9f0636e5bf4afc49c3 | | GLM-4.6V | 59.2 | Not recorded | 69c21a9f0636e5bf4afc49c3 | ### VIGIL Accuracy: 93.1. Result ID: 69c2b0d147f34ce924abd7a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B"}. This record does not assert independent reproduction. ### VIGIL Cold-Start Accuracy: 89.8. Result ID: 69c2b0d147f34ce924abd7a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B","mode":"Cold-Start"}. This record does not assert independent reproduction. ### DDA Accuracy: 88.8. Result ID: 69c2b0d147f34ce924abd7a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Veritas Accuracy: 87.6. Result ID: 69c2b0d147f34ce924abd7a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Co-SPY Accuracy: 84.7. Result ID: 69c2b0d147f34ce924abd79f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### D^3 Accuracy: 80.6. Result ID: 69c2b0d147f34ce924abd79e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AIDE Accuracy: 78.9. Result ID: 69c2b0d147f34ce924abd79c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FakeVLM Accuracy: 77.1. Result ID: 69c2b0d147f34ce924abd7a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UnivFD Accuracy: 76.6. Result ID: 69c2b0d147f34ce924abd799. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-3-Pro Accuracy: 75. Result ID: 69c2b0d147f34ce924abd7a5. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### NPR Accuracy: 73.3. Result ID: 69c2b0d147f34ce924abd79a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### C2P-CLIP Accuracy: 72.2. Result ID: 69c2b0d147f34ce924abd79d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5.2 Accuracy: 71.4. Result ID: 69c2b0d147f34ce924abd7a4. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Kimi-K2.5 Accuracy: 70.2. Result ID: 69c2b0d147f34ce924abd7a3. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SAFE Accuracy: 66.7. Result ID: 69c2b0d147f34ce924abd79b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-8B Accuracy: 59.4. Result ID: 69c2b0d147f34ce924abd7a1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"zero-shot":"true"}. This record does not assert independent reproduction. ### GLM-4.6V Accuracy: 59.2. Result ID: 69c2b0d147f34ce924abd7a2. [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.