# Scene-Text Visual Question Answering on ST-VQA 1.0 (test) Source: [Scene-Text Visual Question Answering on ST-VQA 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:22:33.580Z Evaluation of model performance on the test split of the ST-VQA 1.0 dataset for Scene-Text Visual Question Answering, typically measured using ANLS. 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 | Scene-Text Visual Question Answering | | Dataset (including any stated split) | ST-VQA 1.0 (test) | | Metric | ANLS | | 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 - [ANLS](): Higher is better; unit: PERCENT. ## Recorded results | Method | ANLS | Result date | Report paper | | --- | --- | --- | --- | | DocFormerv2-large | 71.8 | Not recorded | 68fa6f911e209131cea464e7 | | LaTr-large | 69.6 | Not recorded | 68fa6f911e209131cea464e7 | | GIT | 69.6 | Not recorded | 68fa6f911e209131cea464e7 | | LaTr-base | 68.4 | Not recorded | 68fa6f911e209131cea464e7 | | DocFormerv2-base | 68.4 | Not recorded | 68fa6f911e209131cea464e7 | | LaTr-base | 66.8 | Not recorded | 68fa6f911e209131cea464e7 | | PreSTU | 65.5 | Not recorded | 68fa6f911e209131cea464e7 | | TAP + TAG | 60.2 | Not recorded | 68fa6f911e209131cea464e7 | | TAP | 59.7 | Not recorded | 68fa6f911e209131cea464e7 | | LOGOS | 57.9 | Not recorded | 68fa6f911e209131cea464e7 | | SceneGate | 51.6 | Not recorded | 68fa6f911e209131cea464e7 | | SA-M4C | 50.4 | Not recorded | 68fa6f911e209131cea464e7 | | LaAP | 48.5 | Not recorded | 68fa6f911e209131cea464e7 | | M4C | 46.2 | Not recorded | 68fa6f911e209131cea464e7 | ### DocFormerv2-large ANLS: 71.8. Result ID: 6990caed3a6c314849035286. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":"64M","number of parameters":"750M"}. This record does not assert independent reproduction. ### LaTr-large ANLS: 69.6. Result ID: 6990caed3a6c314849035283. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":"64M","number of parameters":"856M"}. This record does not assert independent reproduction. ### GIT ANLS: 69.6. Result ID: 6990caed3a6c314849035284. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":"800M (Proprietary)","number of parameters":"681M"}. This record does not assert independent reproduction. ### LaTr-base ANLS: 68.4. Result ID: 6990caed3a6c314849035282. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":"64M","number of parameters":"311M","training\_set":"ST-VQA + TextVQA"}. This record does not assert independent reproduction. ### DocFormerv2-base ANLS: 68.4. Result ID: 6990caed3a6c314849035285. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":"64M","number of parameters":"232M"}. This record does not assert independent reproduction. ### LaTr-base ANLS: 66.8. Result ID: 6990caed3a6c314849035281. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":"64M","number of parameters":"311M"}. This record does not assert independent reproduction. ### PreSTU ANLS: 65.5. Result ID: 6990caed3a6c314849035280. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":"13M","number of parameters":"237M"}. This record does not assert independent reproduction. ### TAP + TAG ANLS: 60.2. Result ID: 6990caed3a6c31484903527f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"pre-train data":null,"number of parameters":null}. This record does not assert independent reproduction. ### TAP ANLS: 59.7. Result ID: 6990caed3a6c31484903527e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":"200M","number of parameters":null}. This record does not assert independent reproduction. ### LOGOS ANLS: 57.9. Result ID: 6990caed3a6c31484903527d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":null,"number of parameters":null}. This record does not assert independent reproduction. ### SceneGate ANLS: 51.6. Result ID: 6990caed3a6c31484903527c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":null,"number of parameters":null}. This record does not assert independent reproduction. ### SA-M4C ANLS: 50.4. Result ID: 6990caed3a6c31484903527b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":"200M","number of parameters":null}. This record does not assert independent reproduction. ### LaAP ANLS: 48.5. Result ID: 6990caed3a6c31484903527a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":null,"number of parameters":null}. This record does not assert independent reproduction. ### M4C ANLS: 46.2. Result ID: 6990caed3a6c314849035279. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":"200M","number of parameters":null}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.