# GUI Grounding on Screenspot Web Source: [GUI Grounding on Screenspot Web]() Collection index: [llms.txt]() Data updated: 2026-05-19T09:00:01.505Z Evaluation of GUI Grounding performance specifically on the Web subset of the Screenspot dataset, reporting Text and Icon accuracy. 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 | GUI Grounding | | Dataset (including any stated split) | Screenspot Web | | Metric | Text Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Text Accuracy](): Higher is better; unit: PERCENT. - [Icon Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Text Accuracy | Result date | Report paper | | --- | --- | --- | --- | | SE-GA | 91 | Not recorded | 6a0beeb5dbc836b87d82c545 | | OS-Atlas | 90.9 | Not recorded | 6a0beeb5dbc836b87d82c545 | | UI-TARS | 88.7 | Not recorded | 6a0beeb5dbc836b87d82c545 | | Aguvis | 88.3 | Not recorded | 6a0beeb5dbc836b87d82c545 | | Qwen2.5VL | 87.4 | Not recorded | 6a0beeb5dbc836b87d82c545 | | Aria-UI | 86.5 | Not recorded | 6a0beeb5dbc836b87d82c545 | | ShowUI-G | 83 | Not recorded | 68fa75e41e209131cea6a7f9 | | ShowUI | 81.7 | Not recorded | 68fa75e41e209131cea6a7f9 | | OmniParser | 81.3 | Not recorded | 68fa75e41e209131cea6a7f9 | | UGround | 80.4 | Not recorded | 68fa75e41e209131cea6a7f9 | | UGround | 80.4 | Not recorded | 6a0beeb5dbc836b87d82c545 | | Qwen2.5VL | 77.4 | Not recorded | 6a0beeb5dbc836b87d82c545 | | CogAgent | 70.4 | Not recorded | 68fa75e41e209131cea6a7f9 | | SeeClick | 55.7 | Not recorded | 68fa75e41e209131cea6a7f9 | | SeeClick | 55.7 | Not recorded | 6a0beeb5dbc836b87d82c545 | | Fuyu | 33.9 | Not recorded | 68fa75e41e209131cea6a7f9 | | GPT-4o | 12.2 | Not recorded | 6a0beeb5dbc836b87d82c545 | | Qwen2-VL-2B | 8.7 | Not recorded | 68fa75e41e209131cea6a7f9 | ### SE-GA Text Accuracy: 91. Result ID: 6a0c2686fbc373592c026010. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### OS-Atlas Text Accuracy: 90.9. Result ID: 6a0c2686fbc373592c02600e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### UI-TARS Text Accuracy: 88.7. Result ID: 6a0c2686fbc373592c026008. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"72B"}. This record does not assert independent reproduction. ### Aguvis Text Accuracy: 88.3. Result ID: 6a0c2686fbc373592c02600f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### Qwen2.5VL Text Accuracy: 87.4. Result ID: 6a0c2686fbc373592c026009. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"72B"}. This record does not assert independent reproduction. ### Aria-UI Text Accuracy: 86.5. Result ID: 6a0c2686fbc373592c02600a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"23B"}. This record does not assert independent reproduction. ### ShowUI-G Text Accuracy: 83. Result ID: 6993eab33a6c3148491975ca. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"2B","#Train":"119K","Zero-shot":true,"Training Mode":"Grounding data only"}. This record does not assert independent reproduction. ### ShowUI Text Accuracy: 81.7. Result ID: 6993eab33a6c3148491975cb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"2B","#Train":"256K","Zero-shot":true}. This record does not assert independent reproduction. ### OmniParser Text Accuracy: 81.3. Result ID: 6993eab33a6c3148491975c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4V","Zero-shot":true}. This record does not assert independent reproduction. ### UGround Text Accuracy: 80.4. Result ID: 6993eab33a6c3148491975c9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"7B","#Train":"1.3M","Zero-shot":true}. This record does not assert independent reproduction. ### UGround Text Accuracy: 80.4. Result ID: 6a0c2686fbc373592c02600d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### Qwen2.5VL Text Accuracy: 77.4. Result ID: 6a0c2686fbc373592c02600c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### CogAgent Text Accuracy: 70.4. Result ID: 6993eab33a6c3148491975c6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"18B","#Train":"400K","Zero-shot":true}. This record does not assert independent reproduction. ### SeeClick Text Accuracy: 55.7. Result ID: 6993eab33a6c3148491975c7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"9.6B","#Train":"364K","Zero-shot":true}. This record does not assert independent reproduction. ### SeeClick Text Accuracy: 55.7. Result ID: 6a0c2686fbc373592c02600b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"9.6B"}. This record does not assert independent reproduction. ### Fuyu Text Accuracy: 33.9. Result ID: 6993eab33a6c3148491975c5. [Reporting paper]() Recorded evaluation configuration: {"Size":"8B","Zero-shot":true}. This record does not assert independent reproduction. ### GPT-4o Text Accuracy: 12.2. Result ID: 6a0c2686fbc373592c026007. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"-"}. This record does not assert independent reproduction. ### Qwen2-VL-2B Text Accuracy: 8.7. Result ID: 6993eab33a6c3148491975c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Size":"2B","Zero-shot":true}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.