# Visual Question Answering on OK-VQA (Robustness Accuracy) Source: [Visual Question Answering on OK-VQA (Robustness Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:12.999Z Evaluation of model performance on the OK-VQA dataset for Visual Question Answering, measured using specific accuracy metrics under varying perturbation levels (epsilon values). 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) | OK-VQA | | Metric | Accuracy (Clean) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 (Clean)](): Higher is better; unit: PERCENT. - [Accuracy (eps=2/255)](): Higher is better; unit: PERCENT. - [Accuracy (eps=4/255)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Clean) | Result date | Report paper | | --- | --- | --- | --- | | UniTok-MLLM | 59.6 | Not recorded | 699bdef109c33900fcd8041f | | UniTok-MLLM | 53 | Not recorded | 699bdef109c33900fcd8041f | | UniTok-MLLM | 49.2 | Not recorded | 699bdef109c33900fcd8041f | | UniTok-MLLM | 46.7 | Not recorded | 699bdef109c33900fcd8041f | | UniTok-MLLM | 45.1 | Not recorded | 699bdef109c33900fcd8041f | ### UniTok-MLLM Accuracy (Clean): 59.6. Result ID: 699d09a65698665ec4a9ad6b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tokenizer":"clean"}. This record does not assert independent reproduction. ### UniTok-MLLM Accuracy (Clean): 53. Result ID: 699d09a65698665ec4a9ad6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tokenizer":"AT 4/255"}. This record does not assert independent reproduction. ### UniTok-MLLM Accuracy (Clean): 49.2. Result ID: 699d09a65698665ec4a9ad6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tokenizer":"AT 8/255"}. This record does not assert independent reproduction. ### UniTok-MLLM Accuracy (Clean): 46.7. Result ID: 699d09a65698665ec4a9ad6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tokenizer":"AT 12/255"}. This record does not assert independent reproduction. ### UniTok-MLLM Accuracy (Clean): 45.1. Result ID: 699d09a65698665ec4a9ad6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tokenizer":"AT 16/255"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.