# GUI Visual Grounding on ScreenSpot Standard Setting 1.0 Source: [GUI Visual Grounding on ScreenSpot Standard Setting 1.0]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:20.339Z Evaluation of GUI Visual Grounding performance on the ScreenSpot Standard Setting 1.0 dataset, reporting platform-specific accuracy (Mobile, Desktop, Web) for text and icon/widget grounding. 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 Visual Grounding | | Dataset (including any stated split) | ScreenSpot Standard Setting 1.0 | | Metric | Accuracy (Mobile, Text) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [Accuracy (Mobile, Text)](): Higher is better; unit: PERCENT. - [Accuracy (Mobile, Icon/Widget)](): Higher is better; unit: PERCENT. - [Accuracy (Desktop, Text)](): Higher is better; unit: PERCENT. - [Accuracy (Desktop, Icon/Widget)](): Higher is better; unit: PERCENT. - [Accuracy (Web, Text)](): Higher is better; unit: PERCENT. - [Accuracy (Web, Icon/Widget)](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Mobile, Text) | Result date | Report paper | | --- | --- | --- | --- | | UGround-V1-72B | 94.1 | Not recorded | 68fa79851e209131cea7dfab | | UGround-V1-7B | 93 | Not recorded | 68fa79851e209131cea7dfab | | Aria-UI | 92.3 | Not recorded | 68fa79ef1e209131cea80184 | | UGround-V1-2B | 89.4 | Not recorded | 68fa79851e209131cea7dfab | | UGround | 82.8 | Not recorded | 68fa79851e209131cea7dfab | | UGround | 82.8 | Not recorded | 68fa79ef1e209131cea80184 | | SeeClick | 78 | Not recorded | 68fa79851e209131cea7dfab | | SeeClick | 78 | Not recorded | 68fa79ef1e209131cea80184 | | Qwen2-VL | 75.5 | Not recorded | 68fa79ef1e209131cea80184 | | CogAgent | 67 | Not recorded | 68fa79851e209131cea7dfab | | CogAgent | 67 | Not recorded | 68fa79ef1e209131cea80184 | | GPT-4 | 22.6 | Not recorded | 68fa79851e209131cea7dfab | | GPT-4 | 22.6 | Not recorded | 68fa79ef1e209131cea80184 | | GPT-4o | 20.2 | Not recorded | 68fa79851e209131cea7dfab | | GPT-4o | 20.2 | Not recorded | 68fa79ef1e209131cea80184 | ### UGround-V1-72B Accuracy (Mobile, Text): 94.1. Result ID: 698b51ee8d67a41d0a6d0f4b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"72B","Base Model":"Qwen2-VL"}. This record does not assert independent reproduction. ### UGround-V1-7B Accuracy (Mobile, Text): 93. Result ID: 698b51ee8d67a41d0a6d0f4a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"7B","Base Model":"Qwen2-VL"}. This record does not assert independent reproduction. ### Aria-UI Accuracy (Mobile, Text): 92.3. Result ID: 698c556137894ef7d9cd9662. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input Resolution":"3920x2940"}. This record does not assert independent reproduction. ### UGround-V1-2B Accuracy (Mobile, Text): 89.4. Result ID: 698b51ee8d67a41d0a6d0f49. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"2B","Base Model":"Qwen2-VL"}. This record does not assert independent reproduction. ### UGround Accuracy (Mobile, Text): 82.8. Result ID: 698b51ee8d67a41d0a6d0f48. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UGround Accuracy (Mobile, Text): 82.8. Result ID: 698c556137894ef7d9cd9661. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SeeClick Accuracy (Mobile, Text): 78. Result ID: 698b51ee8d67a41d0a6d0f47. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SeeClick Accuracy (Mobile, Text): 78. Result ID: 698c556137894ef7d9cd965f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2-VL Accuracy (Mobile, Text): 75.5. Result ID: 698c556137894ef7d9cd9660. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CogAgent Accuracy (Mobile, Text): 67. Result ID: 698b51ee8d67a41d0a6d0f46. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CogAgent Accuracy (Mobile, Text): 67. Result ID: 698c556137894ef7d9cd965e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4 Accuracy (Mobile, Text): 22.6. Result ID: 698b51ee8d67a41d0a6d0f44. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4 Accuracy (Mobile, Text): 22.6. Result ID: 698c556137894ef7d9cd965c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4o Accuracy (Mobile, Text): 20.2. Result ID: 698b51ee8d67a41d0a6d0f45. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4o Accuracy (Mobile, Text): 20.2. Result ID: 698c556137894ef7d9cd965d. [Reporting 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.