# Entity Recognition on CORD official (test) Source: [Entity Recognition on CORD official (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:43:16.219Z Evaluation of Entity Recognition performance on the official test split of the CORD dataset, typically measured using F1 score. 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 | Entity Recognition | | Dataset (including any stated split) | CORD official (test) | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 37 of 37 | | 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 - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | UDoc | 98.94 | Not recorded | 68fa6d171e209131cea379cd | | DocTr | 98.2 | Not recorded | 68fa70061e209131cea48a43 | | LayoutLMv3\_LARGE | 97.46 | Not recorded | 68fa6d171e209131cea379cd | | BROS\_LARGE | 97.4 | Not recorded | 68fa6d171e209131cea379cd | | BROS\_LARGE | 97.3 | Not recorded | 68fa70061e209131cea48a43 | | FormNet | 97.3 | Not recorded | 68fa70061e209131cea48a43 | | FormNet | 97.28 | Not recorded | 68fa6d171e209131cea379cd | | DocFormer\_LARGE | 97 | Not recorded | 68fa70061e209131cea48a43 | | DocFormer\_LARGE | 96.99 | Not recorded | 68fa6d171e209131cea379cd | | UDoc\* | 96.86 | Not recorded | 68fa6c601e209131cea33a93 | | UDoc | 96.64 | Not recorded | 68fa6c601e209131cea33a93 | | LayoutLMv3\_BASE | 96.56 | Not recorded | 68fa6d171e209131cea379cd | | BROS\_BASE | 96.5 | Not recorded | 68fa70061e209131cea48a43 | | TILT-Large | 96.33 | Not recorded | 68fa6c601e209131cea33a93 | | DocFormer\_BASE | 96.33 | Not recorded | 68fa6d171e209131cea379cd | | TILT\_LARGE | 96.33 | Not recorded | 68fa6d171e209131cea379cd | | DocFormer\_BASE | 96.3 | Not recorded | 68fa70061e209131cea48a43 | | LiLT\_BASE | 96.07 | Not recorded | 68fa6d171e209131cea379cd | | LayoutLMv2-Large | 96.01 | Not recorded | 68fa6c601e209131cea33a93 | | LayoutLMv2\_LARGE | 96.01 | Not recorded | 68fa6d171e209131cea379cd | | LayoutLMv2\_LARGE | 96 | Not recorded | 68fa70061e209131cea48a43 | | BROS\_BASE | 95.73 | Not recorded | 68fa6d171e209131cea379cd | | TILT-Base | 95.11 | Not recorded | 68fa6c601e209131cea33a93 | | TILT\_BASE | 95.11 | Not recorded | 68fa6d171e209131cea379cd | | LayoutLMv2\_BASE | 95 | Not recorded | 68fa70061e209131cea48a43 | | LayoutLM\_LARGE | 95 | Not recorded | 68fa70061e209131cea48a43 | | LayoutLMv2-Base | 94.95 | Not recorded | 68fa6c601e209131cea33a93 | | LayoutLMv2\_BASE | 94.95 | Not recorded | 68fa6d171e209131cea379cd | | LayoutLM-Large | 94.93 | Not recorded | 68fa6c601e209131cea33a93 | | LayoutLM-Base | 94.72 | Not recorded | 68fa6c601e209131cea33a93 | | LayoutLM\_BASE | 94.7 | Not recorded | 68fa70061e209131cea48a43 | | RoBERTa\_LARGE | 93.8 | Not recorded | 68fa6d171e209131cea379cd | | RoBERTa\_BASE | 93.54 | Not recorded | 68fa6d171e209131cea379cd | | BERT-Large | 90.25 | Not recorded | 68fa6c601e209131cea33a93 | | BERT\_LARGE | 90.25 | Not recorded | 68fa6d171e209131cea379cd | | BERT-Base | 89.68 | Not recorded | 68fa6c601e209131cea33a93 | | BERT\_BASE | 89.68 | Not recorded | 68fa6d171e209131cea379cd | ### UDoc F1 Score: 98.94. Result ID: 698f8bcf3a6c314849f9f8f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"272M","Modality":"T+L+I (R)","Image Embedding":"ResNet-50","Not\_Directly\_Comparable":true}. This record does not assert independent reproduction. ### DocTr F1 Score: 98.2. Result ID: 6990f51a3a6c3148490496e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#params":"153M"}. This record does not assert independent reproduction. ### LayoutLMv3\_LARGE F1 Score: 97.46. Result ID: 698f8bcf3a6c314849f9f902. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"368M","Modality":"T+L+I (P)","Image Embedding":"Linear"}. This record does not assert independent reproduction. ### BROS\_LARGE F1 Score: 97.4. Result ID: 698f8bcf3a6c314849f9f8fd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"340M","Modality":"T+L","Image Embedding":"None"}. This record does not assert independent reproduction. ### BROS\_LARGE F1 Score: 97.3. Result ID: 6990f51a3a6c3148490496e7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#params":"340M"}. This record does not assert independent reproduction. ### FormNet F1 Score: 97.3. Result ID: 6990f51a3a6c3148490496ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#params":"345M"}. This record does not assert independent reproduction. ### FormNet F1 Score: 97.28. Result ID: 698f8bcf3a6c314849f9f8fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"345M","Modality":"T+L","Image Embedding":"None"}. This record does not assert independent reproduction. ### DocFormer\_LARGE F1 Score: 97. Result ID: 6990f51a3a6c3148490496e8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#params":"536M"}. This record does not assert independent reproduction. ### DocFormer\_LARGE F1 Score: 96.99. Result ID: 698f8bcf3a6c314849f9f901. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"536M","Modality":"T+L+I (G)","Image Embedding":"ResNet-50"}. This record does not assert independent reproduction. ### UDoc\* F1 Score: 96.86. Result ID: 698f0d7c3a6c314849f54669. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pretraining Source":"IIT-CDIP","Pretraining #Data":"1M","Pretraining Scale":"Region","Pretraining Max #Words":"64x512","Pretraining Modality":"V+L","#Param.":"272M"}. This record does not assert independent reproduction. ### UDoc F1 Score: 96.64. Result ID: 698f0d7c3a6c314849f54668. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pretraining Source":"IIT-CDIP","Pretraining #Data":"1M","Pretraining Scale":"Region","Pretraining Max #Words":"64x512","Pretraining Modality":"V+L","#Param.":"272M"}. This record does not assert independent reproduction. ### LayoutLMv3\_BASE F1 Score: 96.56. Result ID: 698f8bcf3a6c314849f9f8fa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"133M","Modality":"T+L+I (P)","Image Embedding":"Linear"}. This record does not assert independent reproduction. ### BROS\_BASE F1 Score: 96.5. Result ID: 6990f51a3a6c3148490496e2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#params":"110M"}. This record does not assert independent reproduction. ### TILT-Large F1 Score: 96.33. Result ID: 698f0d7c3a6c314849f54667. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pretraining Source":"RVL-CDIP+","Pretraining #Data":"1.1M","Pretraining Scale":"Word","Pretraining Max #Words":"512","Pretraining Modality":"V+L","#Param.":"780M"}. This record does not assert independent reproduction. ### DocFormer\_BASE F1 Score: 96.33. Result ID: 698f8bcf3a6c314849f9f8f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"183M","Modality":"T+L+I (G)","Image Embedding":"ResNet-50"}. This record does not assert independent reproduction. ### TILT\_LARGE F1 Score: 96.33. Result ID: 698f8bcf3a6c314849f9f8ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"780M","Modality":"T+L+I (R)","Image Embedding":"U-Net"}. This record does not assert independent reproduction. ### DocFormer\_BASE F1 Score: 96.3. Result ID: 6990f51a3a6c3148490496e3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#params":"183M"}. This record does not assert independent reproduction. ### LiLT\_BASE F1 Score: 96.07. Result ID: 698f8bcf3a6c314849f9f8f5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"T+L","Image Embedding":"None"}. This record does not assert independent reproduction. ### LayoutLMv2-Large F1 Score: 96.01. Result ID: 698f0d7c3a6c314849f54665. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining Source":"IIT-CDIP","Pretraining #Data":"11M","Pretraining Scale":"Word","Pretraining Max #Words":"512","Pretraining Modality":"V+L","#Param.":"426M"}. This record does not assert independent reproduction. ### LayoutLMv2\_LARGE F1 Score: 96.01. Result ID: 698f8bcf3a6c314849f9f900. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"426M","Modality":"T+L+I (G)","Image Embedding":"ResNeXt101-FPN"}. This record does not assert independent reproduction. ### LayoutLMv2\_LARGE F1 Score: 96. Result ID: 6990f51a3a6c3148490496e9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#params":"426M"}. This record does not assert independent reproduction. ### BROS\_BASE F1 Score: 95.73. Result ID: 698f8bcf3a6c314849f9f8f4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"110M","Modality":"T+L","Image Embedding":"None"}. This record does not assert independent reproduction. ### TILT-Base F1 Score: 95.11. Result ID: 698f0d7c3a6c314849f54666. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pretraining Source":"RVL-CDIP+","Pretraining #Data":"1.1M","Pretraining Scale":"Word","Pretraining Max #Words":"512","Pretraining Modality":"V+L","#Param.":"230M"}. This record does not assert independent reproduction. ### TILT\_BASE F1 Score: 95.11. Result ID: 698f8bcf3a6c314849f9f8f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"230M","Modality":"T+L+I (R)","Image Embedding":"U-Net"}. This record does not assert independent reproduction. ### LayoutLMv2\_BASE F1 Score: 95. Result ID: 6990f51a3a6c3148490496e4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#params":"200M"}. This record does not assert independent reproduction. ### LayoutLM\_LARGE F1 Score: 95. Result ID: 6990f51a3a6c3148490496e6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#params":"343M"}. This record does not assert independent reproduction. ### LayoutLMv2-Base F1 Score: 94.95. Result ID: 698f0d7c3a6c314849f54664. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining Source":"IIT-CDIP","Pretraining #Data":"11M","Pretraining Scale":"Word","Pretraining Max #Words":"512","Pretraining Modality":"V+L","#Param.":"200M"}. This record does not assert independent reproduction. ### LayoutLMv2\_BASE F1 Score: 94.95. Result ID: 698f8bcf3a6c314849f9f8f8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"200M","Modality":"T+L+I (G)","Image Embedding":"ResNeXt101-FPN"}. This record does not assert independent reproduction. ### LayoutLM-Large F1 Score: 94.93. Result ID: 698f0d7c3a6c314849f54663. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining Source":"IIT-CDIP","Pretraining #Data":"11M","Pretraining Scale":"Word","Pretraining Max #Words":"512","Pretraining Modality":"L","#Param.":"343M"}. This record does not assert independent reproduction. ### LayoutLM-Base F1 Score: 94.72. Result ID: 698f0d7c3a6c314849f54662. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining Source":"IIT-CDIP","Pretraining #Data":"11M","Pretraining Scale":"Word","Pretraining Max #Words":"512","Pretraining Modality":"L","#Param.":"113M"}. This record does not assert independent reproduction. ### LayoutLM\_BASE F1 Score: 94.7. Result ID: 6990f51a3a6c3148490496e1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#params":"113M"}. This record does not assert independent reproduction. ### RoBERTa\_LARGE F1 Score: 93.8. Result ID: 698f8bcf3a6c314849f9f8fc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"355M","Modality":"T","Image Embedding":"None"}. This record does not assert independent reproduction. ### RoBERTa\_BASE F1 Score: 93.54. Result ID: 698f8bcf3a6c314849f9f8f3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"125M","Modality":"T","Image Embedding":"None"}. This record does not assert independent reproduction. ### BERT-Large F1 Score: 90.25. Result ID: 698f0d7c3a6c314849f54661. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining Scale":"Word","Pretraining Max #Words":"512","Pretraining Modality":"L","#Param.":"340M"}. This record does not assert independent reproduction. ### BERT\_LARGE F1 Score: 90.25. Result ID: 698f8bcf3a6c314849f9f8fb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"340M","Modality":"T","Image Embedding":"None"}. This record does not assert independent reproduction. ### BERT-Base F1 Score: 89.68. Result ID: 698f0d7c3a6c314849f54660. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining Scale":"Word","Pretraining Max #Words":"512","Pretraining Modality":"L","#Param.":"110M"}. This record does not assert independent reproduction. ### BERT\_BASE F1 Score: 89.68. Result ID: 698f8bcf3a6c314849f9f8f2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"110M","Modality":"T","Image Embedding":"None"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.