# Science Question Answering on ScienceQA SQAimg Source: [Science Question Answering on ScienceQA SQAimg]() Collection index: [llms.txt]() Data updated: 2026-03-18T08:01:43.896Z Evaluation of model performance on the ScienceQA SQAimg dataset for science-related question answering, measured by Accuracy and Average performance retention. 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 | Science Question Answering | | Dataset (including any stated split) | ScienceQA SQAimg | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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. - [Average Performance Retention](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen2-VL 7B | 84.98 | Not recorded | 69ba31a70636e5bf4afc0941 | | ATV-Pruning | 79.08 | Not recorded | 69ba31a70636e5bf4afc0941 | | SparseGPT | 78.53 | Not recorded | 69ba31a70636e5bf4afc0941 | | TAMP | 77.49 | Not recorded | 69ba31a70636e5bf4afc0941 | | Wanda | 76.85 | Not recorded | 69ba31a70636e5bf4afc0941 | | LLaVA-NeXT 8B | 73.28 | Not recorded | 69ba31a70636e5bf4afc0941 | | TAMP | 70 | Not recorded | 69ba31a70636e5bf4afc0941 | | ATV-Pruning | 69.86 | Not recorded | 69ba31a70636e5bf4afc0941 | | Wanda | 69.06 | Not recorded | 69ba31a70636e5bf4afc0941 | | SparseGPT | 68.12 | Not recorded | 69ba31a70636e5bf4afc0941 | | ATV-Pruning | 59.3 | Not recorded | 69ba31a70636e5bf4afc0941 | | SparseGPT | 55.97 | Not recorded | 69ba31a70636e5bf4afc0941 | | TAMP | 55.78 | Not recorded | 69ba31a70636e5bf4afc0941 | | Wanda | 38.67 | Not recorded | 69ba31a70636e5bf4afc0941 | ### Qwen2-VL 7B Accuracy: 84.98. Result ID: 69ba5b8447f34ce924a408d3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2-VL 7B","Sparsity Level":"0%","Pruning Method":"Dense","Pruning Type":"None"}. This record does not assert independent reproduction. ### ATV-Pruning Accuracy: 79.08. Result ID: 69ba5b8447f34ce924a408d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2-VL 7B","Sparsity Level":"60%","Pruning Method":"ATV-Pruning","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. ### SparseGPT Accuracy: 78.53. Result ID: 69ba5b8447f34ce924a408d4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2-VL 7B","Sparsity Level":"60%","Pruning Method":"SparseGPT","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. ### TAMP Accuracy: 77.49. Result ID: 69ba5b8447f34ce924a408d6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2-VL 7B","Sparsity Level":"60%","Pruning Method":"TAMP","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. ### Wanda Accuracy: 76.85. Result ID: 69ba5b8447f34ce924a408d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2-VL 7B","Sparsity Level":"60%","Pruning Method":"Wanda","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. ### LLaVA-NeXT 8B Accuracy: 73.28. Result ID: 69ba5b8447f34ce924a408ca. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT 8B","Sparsity Level":"0%","Pruning Method":"Dense","Pruning Type":"None"}. This record does not assert independent reproduction. ### TAMP Accuracy: 70. Result ID: 69ba5b8447f34ce924a408cd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT 8B","Sparsity Level":"50%","Pruning Method":"TAMP","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. ### ATV-Pruning Accuracy: 69.86. Result ID: 69ba5b8447f34ce924a408ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT 8B","Sparsity Level":"50%","Pruning Method":"ATV-Pruning","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. ### Wanda Accuracy: 69.06. Result ID: 69ba5b8447f34ce924a408cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT 8B","Sparsity Level":"50%","Pruning Method":"Wanda","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. ### SparseGPT Accuracy: 68.12. Result ID: 69ba5b8447f34ce924a408cb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT 8B","Sparsity Level":"50%","Pruning Method":"SparseGPT","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. ### ATV-Pruning Accuracy: 59.3. Result ID: 69ba5b8447f34ce924a408d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT 8B","Sparsity Level":"60%","Pruning Method":"ATV-Pruning","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. ### SparseGPT Accuracy: 55.97. Result ID: 69ba5b8447f34ce924a408cf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT 8B","Sparsity Level":"60%","Pruning Method":"SparseGPT","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. ### TAMP Accuracy: 55.78. Result ID: 69ba5b8447f34ce924a408d1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT 8B","Sparsity Level":"60%","Pruning Method":"TAMP","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. ### Wanda Accuracy: 38.67. Result ID: 69ba5b8447f34ce924a408d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT 8B","Sparsity Level":"60%","Pruning Method":"Wanda","Pruning Type":"unstructured, uniform pruning"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.