# Scene Text Recognition on Standard STR Benchmark Suite Average (test) Source: [Scene Text Recognition on Standard STR Benchmark Suite Average (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:35:18.047Z Evaluation of Scene Text Recognition performance on the test split average results of the Standard STR Benchmark Suite. 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 Recognition | | Dataset (including any stated split) | Standard STR Benchmark Suite Average (test) | | Metric | Average 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 - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MGP-STR Fuse | 93.35 | Not recorded | 68fa6dac1e209131cea3b5f6 | | MGP-STR Vision | 92.73 | Not recorded | 68fa6dac1e209131cea3b5f6 | | ABINet | 92.6 | Not recorded | 68fa6dac1e209131cea3b5f6 | | VisionLAN | 91.2 | Not recorded | 68fa6dac1e209131cea3b5f6 | | SRN | 90.4 | Not recorded | 68fa6dac1e209131cea3b5f6 | | MASTER | 89.5 | Not recorded | 68fa6dac1e209131cea3b5f6 | | SATRN | 88.6 | Not recorded | 68fa6dac1e209131cea3b5f6 | | TextScanner | 88.5 | Not recorded | 68fa6dac1e209131cea3b5f6 | | RobustScanner | 88.4 | Not recorded | 68fa6dac1e209131cea3b5f6 | | SE-ASTER | 88.3 | Not recorded | 68fa6dac1e209131cea3b5f6 | | DAN | 87.2 | Not recorded | 68fa6dac1e209131cea3b5f6 | | ESIR | 87.1 | Not recorded | 68fa6dac1e209131cea3b5f6 | | ViTSTR | 85.6 | Not recorded | 68fa6dac1e209131cea3b5f6 | | TBRA | 84.6 | Not recorded | 68fa6dac1e209131cea3b5f6 | ### MGP-STR Fuse Average Accuracy: 93.35. Result ID: 698fd3133a6c314849fc1fc4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### MGP-STR Vision Average Accuracy: 92.73. Result ID: 698fd3133a6c314849fc1fc3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### ABINet Average Accuracy: 92.6. Result ID: 698fd3133a6c314849fc1fc2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### VisionLAN Average Accuracy: 91.2. Result ID: 698fd3133a6c314849fc1fc1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### SRN Average Accuracy: 90.4. Result ID: 698fd3133a6c314849fc1fc0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### MASTER Average Accuracy: 89.5. Result ID: 698fd3133a6c314849fc1fbf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### SATRN Average Accuracy: 88.6. Result ID: 698fd3133a6c314849fc1fbe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### TextScanner Average Accuracy: 88.5. Result ID: 698fd3133a6c314849fc1fbd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### RobustScanner Average Accuracy: 88.4. Result ID: 698fd3133a6c314849fc1fbc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### SE-ASTER Average Accuracy: 88.3. Result ID: 698fd3133a6c314849fc1fbb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### DAN Average Accuracy: 87.2. Result ID: 698fd3133a6c314849fc1fba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### ESIR Average Accuracy: 87.1. Result ID: 698fd3133a6c314849fc1fb9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### ViTSTR Average Accuracy: 85.6. Result ID: 698fd3133a6c314849fc1fb8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. ### TBRA Average Accuracy: 84.6. Result ID: 698fd3133a6c314849fc1fb7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Data":"MJ and ST","Lexicon":"None"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.