# Video Scene Identification on VSI-Bench Source: [Video Scene Identification on VSI-Bench]() Collection index: [llms.txt]() Data updated: 2026-03-04T18:46:50.837Z Evaluation of video scene identification capabilities using the VSI-Bench dataset, 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 | Video Scene Identification | | Dataset (including any stated split) | VSI-Bench | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 | | --- | --- | --- | --- | | APPO | 38.2 | Not recorded | 69a5195f2d603e6de3e3c777 | | APPO | 36.9 | Not recorded | 69a5195f2d603e6de3e3c777 | | DAPO | 36.7 | Not recorded | 69a5195f2d603e6de3e3c777 | | DAPO | 36.6 | Not recorded | 69a5195f2d603e6de3e3c777 | | GRPO | 35.9 | Not recorded | 69a5195f2d603e6de3e3c777 | | GRPO | 34.8 | Not recorded | 69a5195f2d603e6de3e3c777 | | SFT | 32.9 | Not recorded | 69a5195f2d603e6de3e3c777 | | SFT | 31.8 | Not recorded | 69a5195f2d603e6de3e3c777 | | Base Model | 29.2 | Not recorded | 69a5195f2d603e6de3e3c777 | | Base Model | 27.8 | Not recorded | 69a5195f2d603e6de3e3c777 | ### APPO Accuracy: 38.2. Result ID: 69a87e046dbb7075b950bb67. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-3B","Resolution":"224x224","Sampling Rate":"1 fps","Max Frames":"60"}. This record does not assert independent reproduction. ### APPO Accuracy: 36.9. Result ID: 69a87e046dbb7075b950bb6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B","Resolution":"224x224","Sampling Rate":"1 fps","Max Frames":"60"}. This record does not assert independent reproduction. ### DAPO Accuracy: 36.7. Result ID: 69a87e046dbb7075b950bb66. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-3B","Resolution":"224x224","Sampling Rate":"1 fps","Max Frames":"60"}. This record does not assert independent reproduction. ### DAPO Accuracy: 36.6. Result ID: 69a87e046dbb7075b950bb6b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B","Resolution":"224x224","Sampling Rate":"1 fps","Max Frames":"60"}. This record does not assert independent reproduction. ### GRPO Accuracy: 35.9. Result ID: 69a87e046dbb7075b950bb6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B","Resolution":"224x224","Sampling Rate":"1 fps","Max Frames":"60"}. This record does not assert independent reproduction. ### GRPO Accuracy: 34.8. Result ID: 69a87e046dbb7075b950bb65. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-3B","Resolution":"224x224","Sampling Rate":"1 fps","Max Frames":"60"}. This record does not assert independent reproduction. ### SFT Accuracy: 32.9. Result ID: 69a87e046dbb7075b950bb64. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-3B","Resolution":"224x224","Sampling Rate":"1 fps","Max Frames":"60"}. This record does not assert independent reproduction. ### SFT Accuracy: 31.8. Result ID: 69a87e046dbb7075b950bb69. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B","Resolution":"224x224","Sampling Rate":"1 fps","Max Frames":"60"}. This record does not assert independent reproduction. ### Base Model Accuracy: 29.2. Result ID: 69a87e046dbb7075b950bb63. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-3B","Resolution":"224x224","Sampling Rate":"1 fps","Max Frames":"60"}. This record does not assert independent reproduction. ### Base Model Accuracy: 27.8. Result ID: 69a87e046dbb7075b950bb68. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B","Resolution":"224x224","Sampling Rate":"1 fps","Max Frames":"60"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.