# Video Question Answering on Video-MME (p@1, p@4, m@4) Source: [Video Question Answering on Video-MME (p@1, p@4, m@4)]() Collection index: [llms.txt]() Data updated: 2026-07-07T07:55:25.434Z Evaluation of Video Question Answering performance on the Video-MME dataset, reporting Precision at K (K=1, 4) and Mean at 4 scores. 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) | Video-MME | | Metric | P@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [P@1](): Higher is better; unit: PERCENT. - [P@4](): Higher is better; unit: PERCENT. - [M@4](): Higher is better; unit: PERCENT. ## Recorded results | Method | P@1 | Result date | Report paper | | --- | --- | --- | --- | | GPT-5.2 | 67.7 | Not recorded | 6a4c87dc85dba69fef8b2321 | | Qwen3-VL-4B-Instruct | 63.7 | Not recorded | 6a4c87dc85dba69fef8b2321 | | Qwen3-VL-8B-Instruct | 63.7 | Not recorded | 6a4c87dc85dba69fef8b2321 | | VSeek-VETL | 61.4 | Not recorded | 6a4c87dc85dba69fef8b2321 | | VSeek-GPT | 61.2 | Not recorded | 6a4c87dc85dba69fef8b2321 | | Qwen3-VL-8B-Thinking | 60.3 | Not recorded | 6a4c87dc85dba69fef8b2321 | | VSeek-EM | 59.3 | Not recorded | 6a4c87dc85dba69fef8b2321 | | Qwen3-VL-4B-Thinking | 58.1 | Not recorded | 6a4c87dc85dba69fef8b2321 | | VideoTree | 56.3 | Not recorded | 6a4c87dc85dba69fef8b2321 | | Naive RAG | 55 | Not recorded | 6a4c87dc85dba69fef8b2321 | | InternVL-3.5-4B | 53.1 | Not recorded | 6a4c87dc85dba69fef8b2321 | ### GPT-5.2 P@1: 67.7. Result ID: 6a4cb0d260b88bb339c7f7da. [Reporting paper]() Recorded evaluation configuration: {"frames":"64"}. This record does not assert independent reproduction. ### Qwen3-VL-4B-Instruct P@1: 63.7. Result ID: 6a4cb0d260b88bb339c7f7de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"4B"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Instruct P@1: 63.7. Result ID: 6a4cb0d260b88bb339c7f7e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"8B"}. This record does not assert independent reproduction. ### VSeek-VETL P@1: 61.4. Result ID: 6a4cb0d260b88bb339c7f7e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"reward\_type":"VETL"}. This record does not assert independent reproduction. ### VSeek-GPT P@1: 61.2. Result ID: 6a4cb0d260b88bb339c7f7db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"GPT-5.2"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Thinking P@1: 60.3. Result ID: 6a4cb0d260b88bb339c7f7df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"8B"}. This record does not assert independent reproduction. ### VSeek-EM P@1: 59.3. Result ID: 6a4cb0d260b88bb339c7f7e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"reward\_type":"exact-match"}. This record does not assert independent reproduction. ### Qwen3-VL-4B-Thinking P@1: 58.1. Result ID: 6a4cb0d260b88bb339c7f7dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"4B"}. This record does not assert independent reproduction. ### VideoTree P@1: 56.3. Result ID: 6a4cb0d260b88bb339c7f7e2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Naive RAG P@1: 55. Result ID: 6a4cb0d260b88bb339c7f7e1. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL-3.5-4B P@1: 53.1. Result ID: 6a4cb0d260b88bb339c7f7dc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"parameters":"4B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.