# Video Anomaly Question Answering on UCF-Crime Source: [Video Anomaly Question Answering on UCF-Crime]() Collection index: [llms.txt]() Data updated: 2026-02-27T11:10:16.990Z Evaluation of Video Anomaly Question Answering performance on the UCF-Crime dataset, measured by accuracy 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 Anomaly Question Answering | | Dataset (including any stated split) | UCF-Crime | | Metric | Accuracy (w/o think) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 (w/o think)](): Higher is better; unit: PERCENT. - [Accuracy (w/ think)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (w/o think) | Result date | Report paper | | --- | --- | --- | --- | | SRVAU-R1 | 92.82 | Not recorded | 6981812ea8b01e76cc8e231c | | Qwen2.5-VL-7B | 92.03 | Not recorded | 6981812ea8b01e76cc8e231c | | VAU-R1 | 92.03 | Not recorded | 6981812ea8b01e76cc8e231c | | Qwen2.5-VL-3B | 91.63 | Not recorded | 6981812ea8b01e76cc8e231c | | InternVL2.5-8B-MPO | 89.64 | Not recorded | 6981812ea8b01e76cc8e231c | | Qwen2-VL-2B | 87.25 | Not recorded | 6981812ea8b01e76cc8e231c | | HolmesVAU | 86.45 | Not recorded | 6981812ea8b01e76cc8e231c | | InternVL2.5-2B | 84.86 | Not recorded | 6981812ea8b01e76cc8e231c | ### SRVAU-R1 Accuracy (w/o think): 92.82. Result ID: 69a17b8f35dfcabb00e759d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Accuracy (w/o think): 92.03. Result ID: 69a17b8f35dfcabb00e759ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VAU-R1 Accuracy (w/o think): 92.03. Result ID: 69a17b8f35dfcabb00e759cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Accuracy (w/o think): 91.63. Result ID: 69a17b8f35dfcabb00e759cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2.5-8B-MPO Accuracy (w/o think): 89.64. Result ID: 69a17b8f35dfcabb00e759cb. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2-VL-2B Accuracy (w/o think): 87.25. Result ID: 69a17b8f35dfcabb00e759cc. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### HolmesVAU Accuracy (w/o think): 86.45. Result ID: 69a17b8f35dfcabb00e759ce. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2.5-2B Accuracy (w/o think): 84.86. Result ID: 69a17b8f35dfcabb00e759c9. [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.