# Action Reasoning on Video-MME Long (test) Source: [Action Reasoning on Video-MME Long (test)]() Collection index: [llms.txt]() Data updated: 2026-05-08T10:21:04.487Z Evaluation of Action Reasoning performance on the test split of the Video-MME Long subset, specifically covering queries between 1800s and 3600s, measured by 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 | Action Reasoning | | Dataset (including any stated split) | Video-MME Long (1800s-3600s) (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 2 of 2 | | 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 | | --- | --- | --- | --- | | EC-RAG | 46.67 | Not recorded | 69fd6e1a5497b3b670c8946a | | Qwen3-VL-8B | 43.89 | Not recorded | 69fd6e1a5497b3b670c8946a | ### EC-RAG Accuracy: 46.67. Result ID: 69fdb90847f34ce924e1487e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B"}. This record does not assert independent reproduction. ### Qwen3-VL-8B Accuracy: 43.89. Result ID: 69fdb90847f34ce924e1487d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B","Configuration":"Baseline"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.