# Visual Question Answering on GQA (dev) Source: [Visual Question Answering on GQA (dev)]() Collection index: [llms.txt]() Data updated: 2026-02-27T10:00:48.618Z Evaluation of model performance on the development split of the GQA dataset for visual question answering, typically 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 | Visual Question Answering | | Dataset (including any stated split) | GQA (dev) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 | | --- | --- | --- | --- | | RADIOv2.5-H | 63.8 | Not recorded | 68fa76e01e209131cea6f909 | | RADIOv2.1-H | 63.4 | Not recorded | 68fa76e01e209131cea6f909 | | RADIOv2.5-L | 63.4 | Not recorded | 68fa76e01e209131cea6f909 | | RADIOv2.5-g | 63.4 | Not recorded | 68fa76e01e209131cea6f909 | | SigLIP-SO400M | 63.1 | Not recorded | 68fa76e01e209131cea6f909 | | RADIOv2.1-H | 62.7 | Not recorded | 68fa76e01e209131cea6f909 | | OpenAI-CLIP | 62.4 | Not recorded | 68fa76e01e209131cea6f909 | ### RADIOv2.5-H Accuracy: 63.8. Result ID: 69a16b3d35dfcabb00e6ec12. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Resolution":"768^2","Tokens/im":"196","LLM":"MN-Minitron-8B","Data mixture":"LLaVA1.6"}. This record does not assert independent reproduction. ### RADIOv2.1-H Accuracy: 63.4. Result ID: 69a16b3d35dfcabb00e6ec0e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Resolution":"512^2","Tokens/im":"196","LLM":"MN-Minitron-8B","Data mixture":"LLaVA1.6"}. This record does not assert independent reproduction. ### RADIOv2.5-L Accuracy: 63.4. Result ID: 69a16b3d35dfcabb00e6ec11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Resolution":"768^2","Tokens/im":"196","LLM":"MN-Minitron-8B","Data mixture":"LLaVA1.6"}. This record does not assert independent reproduction. ### RADIOv2.5-g Accuracy: 63.4. Result ID: 69a16b3d35dfcabb00e6ec13. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Resolution":"672^2","Tokens/im":"196","LLM":"MN-Minitron-8B","Data mixture":"LLaVA1.6"}. This record does not assert independent reproduction. ### SigLIP-SO400M Accuracy: 63.1. Result ID: 69a16b3d35dfcabb00e6ec10. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Resolution":"384^2","Tokens/im":"196","LLM":"MN-Minitron-8B","Data mixture":"LLaVA1.6"}. This record does not assert independent reproduction. ### RADIOv2.1-H Accuracy: 62.7. Result ID: 69a16b3d35dfcabb00e6ec0f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Resolution":"768^2","Tokens/im":"196","LLM":"MN-Minitron-8B","Data mixture":"LLaVA1.6"}. This record does not assert independent reproduction. ### OpenAI-CLIP Accuracy: 62.4. Result ID: 69a16b3d35dfcabb00e6ec0d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Resolution":"336^2","Tokens/im":"196","LLM":"MN-Minitron-8B","Data mixture":"LLaVA1.6"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.