# Visually-rich Information Extraction on SROIE (test) Source: [Visually-rich Information Extraction on SROIE (test)]() Collection index: [llms.txt]() Data updated: 2026-05-27T09:29:34.058Z Evaluation of Visually-rich Information Extraction performance on the test split of the SROIE dataset, 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 | Visually-rich Information Extraction | | Dataset (including any stated split) | SROIE (test) | | Metric | ANLS | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 | | --- | --- | --- | --- | | Qwen2-VL-7B | 98.05 | Not recorded | 68fa78131e209131cea76a9c | | Qwen2-VL-7B | 97.74 | Not recorded | 68fa78131e209131cea76a9c | | Qwen2-VL-7B | 97.5 | Not recorded | 68fa78131e209131cea76a9c | | InternVL2-8B-CoB | 97.181 | Not recorded | 68fa78c91e209131cea7a86a | | DocOwl 1.5-CoB | 96.522 | Not recorded | 68fa78c91e209131cea7a86a | | DocOwl 1.5-R | 96.35 | Not recorded | 68fa78c91e209131cea7a86a | | Qwen2.5-VL-CoB | 96.07 | Not recorded | 68fa78c91e209131cea7a86a | | InternVL2-2B-CoB | 95.94 | Not recorded | 68fa78c91e209131cea7a86a | | DocOwl 1.5\* | 95.67 | Not recorded | 68fa78c91e209131cea7a86a | | Qwen2.5-VL-R | 95.52 | Not recorded | 68fa78c91e209131cea7a86a | | Qwen2.5-VL\* | 94.99 | Not recorded | 68fa78c91e209131cea7a86a | | InternVL2-8B-R | 94.31 | Not recorded | 68fa78c91e209131cea7a86a | | InternVL2-40B | 92.03 | Not recorded | 68fa78c91e209131cea7a86a | | GPT-4o | 91.87 | Not recorded | 68fa78c91e209131cea7a86a | | InternVL2-8B\* | 90.39 | Not recorded | 68fa78c91e209131cea7a86a | | Visual CoT | 88.78 | Not recorded | 68fa78c91e209131cea7a86a | | InternVL2-2B-R | 88.02 | Not recorded | 68fa78c91e209131cea7a86a | | InternVL2-2B\* | 87.11 | Not recorded | 68fa78c91e209131cea7a86a | | TextCoT | 81.62 | Not recorded | 68fa78c91e209131cea7a86a | ### Qwen2-VL-7B ANLS: 98.05. Result ID: 69957bfb3badfaffe673355a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Data":"RIDGE + RIDGE-DS"}. This record does not assert independent reproduction. ### Qwen2-VL-7B ANLS: 97.74. Result ID: 69957bfb3badfaffe6733559. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Data":"RIDGE"}. This record does not assert independent reproduction. ### Qwen2-VL-7B ANLS: 97.5. Result ID: 69957bfb3badfaffe6733558. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Data":"Original"}. This record does not assert independent reproduction. ### InternVL2-8B-CoB ANLS: 97.181. Result ID: 6a16b96dfbc373592c103146. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Doc-CoB":"true"}. This record does not assert independent reproduction. ### DocOwl 1.5-CoB ANLS: 96.522. Result ID: 6a16b96dfbc373592c103140. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Doc-CoB":"true"}. This record does not assert independent reproduction. ### DocOwl 1.5-R ANLS: 96.35. Result ID: 6a16b96dfbc373592c10313f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Reasoning tasks":"true"}. This record does not assert independent reproduction. ### Qwen2.5-VL-CoB ANLS: 96.07. Result ID: 6a16b96dfbc373592c10313d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Doc-CoB":"true"}. This record does not assert independent reproduction. ### InternVL2-2B-CoB ANLS: 95.94. Result ID: 6a16b96dfbc373592c103143. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Doc-CoB":"true"}. This record does not assert independent reproduction. ### DocOwl 1.5\* ANLS: 95.67. Result ID: 6a16b96dfbc373592c10313e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT baseline":"true"}. This record does not assert independent reproduction. ### Qwen2.5-VL-R ANLS: 95.52. Result ID: 6a16b96dfbc373592c10313c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Reasoning tasks":"true"}. This record does not assert independent reproduction. ### Qwen2.5-VL\* ANLS: 94.99. Result ID: 6a16b96dfbc373592c10313b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT baseline":"true"}. This record does not assert independent reproduction. ### InternVL2-8B-R ANLS: 94.31. Result ID: 6a16b96dfbc373592c103145. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Reasoning tasks":"true"}. This record does not assert independent reproduction. ### InternVL2-40B ANLS: 92.03. Result ID: 6a16b96dfbc373592c103147. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scale":"40B"}. This record does not assert independent reproduction. ### GPT-4o ANLS: 91.87. Result ID: 6a16b96dfbc373592c103148. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2-8B\* ANLS: 90.39. Result ID: 6a16b96dfbc373592c103144. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"SFT baseline":"true"}. This record does not assert independent reproduction. ### Visual CoT ANLS: 88.78. Result ID: 6a16b96dfbc373592c10314a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2-2B-R ANLS: 88.02. Result ID: 6a16b96dfbc373592c103142. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Reasoning tasks":"true"}. This record does not assert independent reproduction. ### InternVL2-2B\* ANLS: 87.11. Result ID: 6a16b96dfbc373592c103141. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"SFT baseline":"true"}. This record does not assert independent reproduction. ### TextCoT ANLS: 81.62. Result ID: 6a16b96dfbc373592c103149. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.