# Video Question Answering on VideoMME (Aspect Metrics) Source: [Video Question Answering on VideoMME (Aspect Metrics)]() Collection index: [llms.txt]() Data updated: 2026-04-21T10:17:33.580Z Evaluation of model performance on the VideoMME dataset for Video Question Answering, focusing on aspect-based reasoning scores including Temporal, Spatial, Action, and Object understanding. 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 Question Answering | | Dataset (including any stated split) | VideoMME | | Metric | VYR | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [VYR](): Higher is better; unit: PERCENT. - [Temporal](): Higher is better; unit: PERCENT. - [Spatial](): Higher is better; unit: PERCENT. - [Action](): Higher is better; unit: PERCENT. - [Object](): Higher is better; unit: PERCENT. - [TIHR](): Higher is better; unit: PERCENT. - [WHR](): Higher is better; unit: PERCENT. - [SCSI](): Higher is better; unit: SCALAR. - [HRR](): Higher is better; unit: PERCENT. - [HSR](): Lower is better; unit: SCALAR. - [TIB](): Higher is better; unit: PERCENT. - [ICR](): Lower is better; unit: SCALAR. - [SGLI](): Higher is better; unit: SCALAR. - [TLSR](): Lower is better; unit: SCALAR. - [ASLSR](): Higher is better; unit: SCALAR. - [AALSR](): Higher is better; unit: SCALAR. - [SRLSR](): Lower is better; unit: SCALAR. - [Overall Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | VYR | Result date | Report paper | | --- | --- | --- | --- | | Baseline+CoT+SFT | 30.9 | Not recorded | 69e7049f7d0172140ec7ed93 | | Baseline+SFT | 20.7 | Not recorded | 69e7049f7d0172140ec7ed93 | | Baseline (Qwen3-VL-8B-Instruct) | 19.3 | Not recorded | 69e7049f7d0172140ec7ed93 | | Baseline+CoT | 19 | Not recorded | 69e7049f7d0172140ec7ed93 | | Internvl3.5-VL-241B | 14.5 | Not recorded | 69e7049f7d0172140ec7ed93 | | Qwen3-VL-30B | 13.8 | Not recorded | 69e7049f7d0172140ec7ed93 | | Qwen3-VL-235B | 12.7 | Not recorded | 69e7049f7d0172140ec7ed93 | | VTHM-MoE | 4.1 | Not recorded | 69e7049f7d0172140ec7ed93 | | Gemini-3.1-Pro | 0.7 | Not recorded | 69e7049f7d0172140ec7ed93 | ### Baseline+CoT+SFT VYR: 30.9. Result ID: 69e74eac47f34ce924ce2815. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B-Instruct","Chain-of-Thought":"true","Supervised Fine-Tuning":"true"}. This record does not assert independent reproduction. ### Baseline+SFT VYR: 20.7. Result ID: 69e74eac47f34ce924ce2814. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B-Instruct","Supervised Fine-Tuning":"true"}. This record does not assert independent reproduction. ### Baseline (Qwen3-VL-8B-Instruct) VYR: 19.3. Result ID: 69e74eac47f34ce924ce2812. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B-Instruct"}. This record does not assert independent reproduction. ### Baseline+CoT VYR: 19. Result ID: 69e74eac47f34ce924ce2813. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B-Instruct","Chain-of-Thought":"true"}. This record does not assert independent reproduction. ### Internvl3.5-VL-241B VYR: 14.5. Result ID: 69e74eac47f34ce924ce2811. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"241B"}. This record does not assert independent reproduction. ### Qwen3-VL-30B VYR: 13.8. Result ID: 69e74eac47f34ce924ce280f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"30B"}. This record does not assert independent reproduction. ### Qwen3-VL-235B VYR: 12.7. Result ID: 69e74eac47f34ce924ce2810. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"235B"}. This record does not assert independent reproduction. ### VTHM-MoE VYR: 4.1. Result ID: 69e74eac47f34ce924ce2816. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-3.1-Pro VYR: 0.7. Result ID: 69e74eac47f34ce924ce280e. [Reporting paper]() [Method origin 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.