# Long-form video understanding on Video-MME w/o sub. Source: [Long-form video understanding on Video-MME w/o sub.]() Collection index: [llms.txt]() Data updated: 2026-05-27T09:00:44.356Z Evaluation of long-form video understanding capabilities on the Video-MME dataset subset excluding subtitles. 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 | Long-form video understanding | | Dataset (including any stated split) | Video-MME w/o sub. | | Metric | Score (w/o sub) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [Score (w/o sub)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Score (w/o sub) | Result date | Report paper | | --- | --- | --- | --- | | DynFrame-8B | 72.3 | Not recorded | 6a167a7fdbd7150506f7ff1a | | Qwen3-VL (Thinking) | 71.8 | Not recorded | 6a167a7fdbd7150506f7ff1a | | DynFrame-4B | 69.5 | Not recorded | 6a167a7fdbd7150506f7ff1a | | Qwen3-VL (Thinking) | 68.9 | Not recorded | 6a167a7fdbd7150506f7ff1a | | VideoChat-R1.5 | 67.1 | Not recorded | 6a167a7fdbd7150506f7ff1a | | Video-o3 | 66.5 | Not recorded | 6a167a7fdbd7150506f7ff1a | | InternVL3 | 66.3 | Not recorded | 6a167a7fdbd7150506f7ff1a | | LOVE-R1 | 66.2 | Not recorded | 6a167a7fdbd7150506f7ff1a | | VideoZoomer | 65.2 | Not recorded | 6a167a7fdbd7150506f7ff1a | | Qwen2.5-VL | 65.1 | Not recorded | 6a167a7fdbd7150506f7ff1a | | VITAL | 64.1 | Not recorded | 6a167a7fdbd7150506f7ff1a | | Video-R1-7B | 61.4 | Not recorded | 6a167a7fdbd7150506f7ff1a | | Temporal-RLT | 57.6 | Not recorded | 6a167a7fdbd7150506f7ff1a | ### DynFrame-8B Score (w/o sub): 72.3. Result ID: 6a16b0ccfbc373592c0ff8b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### Qwen3-VL (Thinking) Score (w/o sub): 71.8. Result ID: 6a16b0ccfbc373592c0ff8af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### DynFrame-4B Score (w/o sub): 69.5. Result ID: 6a16b0ccfbc373592c0ff8b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"4B"}. This record does not assert independent reproduction. ### Qwen3-VL (Thinking) Score (w/o sub): 68.9. Result ID: 6a16b0ccfbc373592c0ff8ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"4B"}. This record does not assert independent reproduction. ### VideoChat-R1.5 Score (w/o sub): 67.1. Result ID: 6a16b0ccfbc373592c0ff8b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Video-o3 Score (w/o sub): 66.5. Result ID: 6a16b0ccfbc373592c0ff8b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### InternVL3 Score (w/o sub): 66.3. Result ID: 6a16b0ccfbc373592c0ff8ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"8B"}. This record does not assert independent reproduction. ### LOVE-R1 Score (w/o sub): 66.2. Result ID: 6a16b0ccfbc373592c0ff8b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### VideoZoomer Score (w/o sub): 65.2. Result ID: 6a16b0ccfbc373592c0ff8b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL Score (w/o sub): 65.1. Result ID: 6a16b0ccfbc373592c0ff8ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### VITAL Score (w/o sub): 64.1. Result ID: 6a16b0ccfbc373592c0ff8b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Video-R1-7B Score (w/o sub): 61.4. Result ID: 6a16b0ccfbc373592c0ff8b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Temporal-RLT Score (w/o sub): 57.6. Result ID: 6a16b0ccfbc373592c0ff8b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.