# Video Anomaly Question Answering on MSAD Source: [Video Anomaly Question Answering on MSAD]() Collection index: [llms.txt]() Data updated: 2026-02-27T11:10:16.940Z Evaluation of model performance on the MSAD dataset for the Video Anomaly Question Answering task. 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) | MSAD | | Metric | Acc (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 - [Acc (w/o think)](): Higher is better; unit: PERCENT. - [Acc (w/ think)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Acc (w/o think) | Result date | Report paper | | --- | --- | --- | --- | | SRVAU-R1 | 89.58 | Not recorded | 6981812ea8b01e76cc8e231c | | VAU-R1 | 88.33 | Not recorded | 6981812ea8b01e76cc8e231c | | Qwen2.5-VL-3B | 85.83 | Not recorded | 6981812ea8b01e76cc8e231c | | HolmesVAU | 85 | Not recorded | 6981812ea8b01e76cc8e231c | | Qwen2.5-VL-7B | 84.58 | Not recorded | 6981812ea8b01e76cc8e231c | | InternVL2.5-8B-MPO | 82.5 | Not recorded | 6981812ea8b01e76cc8e231c | | Qwen2-VL-2B | 77.08 | Not recorded | 6981812ea8b01e76cc8e231c | | InternVL2.5-2B | 76.67 | Not recorded | 6981812ea8b01e76cc8e231c | ### SRVAU-R1 Acc (w/o think): 89.58. Result ID: 69a17b8f35dfcabb00e759c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VAU-R1 Acc (w/o think): 88.33. Result ID: 69a17b8f35dfcabb00e759bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Acc (w/o think): 85.83. Result ID: 69a17b8f35dfcabb00e759bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### HolmesVAU Acc (w/o think): 85. Result ID: 69a17b8f35dfcabb00e759be. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Acc (w/o think): 84.58. Result ID: 69a17b8f35dfcabb00e759ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2.5-8B-MPO Acc (w/o think): 82.5. Result ID: 69a17b8f35dfcabb00e759bb. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2-VL-2B Acc (w/o think): 77.08. Result ID: 69a17b8f35dfcabb00e759bc. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2.5-2B Acc (w/o think): 76.67. Result ID: 69a17b8f35dfcabb00e759b9. [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.