# Visual Grounding on ScreenSpot-Pro 1.0 (test) Source: [Visual Grounding on ScreenSpot-Pro 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:40:48.934Z Evaluation of Visual Grounding performance on the test split of the ScreenSpot-Pro 1.0 dataset, reporting scores across various domains (Development, Creative, CAD, Scientific, Office, OS). 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 | Visual Grounding | | Dataset (including any stated split) | ScreenSpot-Pro 1.0 (test) | | Metric | Development Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 27 of 27 | | 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 - [Development Score](): Higher is better; unit: SCALAR. - [Creative Score](): Higher is better; unit: SCALAR. - [CAD Score](): Higher is better; unit: SCALAR. - [Scientific Score](): Higher is better; unit: SCALAR. - [Office Score](): Higher is better; unit: SCALAR. - [OS Score](): Higher is better; unit: SCALAR. - [Overall Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Development Score | Result date | Report paper | | --- | --- | --- | --- | | Qwen3VL-32B-Instruct | 71.6 | Not recorded | 6938fe876cfd488761a53c83 | | UI-TARS-1.5 | 63.9 | Not recorded | 6938fe876cfd488761a53c83 | | Qwen3VL-8B-Instruct | 61.5 | Not recorded | 6938fe876cfd488761a53c83 | | UI-Venus-72B | 59.5 | Not recorded | 6938fe876cfd488761a53c83 | | GTA1-7B | 58.9 | Not recorded | 6938fe876cfd488761a53c83 | | GUI-Cursor-7B | 57.5 | Not recorded | 6938fe876cfd488761a53c83 | | GTA1-72B | 57.2 | Not recorded | 6938fe876cfd488761a53c83 | | UI-INS-32B | 55.8 | Not recorded | 6938fe876cfd488761a53c83 | | Seed1.5-VL | 53.8 | Not recorded | 6938fe876cfd488761a53c83 | | GUI-Spotlight | 53.3 | Not recorded | 6938fe876cfd488761a53c83 | | Qwen3VL-8B-Instruct | 52.8 | Not recorded | 6938fe876cfd488761a53c83 | | UI-TARS-1.5-7B | 51.8 | Not recorded | 6938fe876cfd488761a53c83 | | RegionFocus (Qwen2.5VL-72B) | 51.2 | Not recorded | 6938fe876cfd488761a53c83 | | Qwen2.5-VL-32B-Instruct | 48.8 | Not recorded | 6938fe876cfd488761a53c83 | | HyperClick | 46.9 | Not recorded | 6938fe876cfd488761a53c83 | | V2P-7B | 46.8 | Not recorded | 6938fe876cfd488761a53c83 | | GMS (Gemini-2.5-Flash-Lite) | 44.8 | Not recorded | 6938fe876cfd488761a53c83 | | SE-GUI-7B | 44.5 | Not recorded | 6938fe876cfd488761a53c83 | | GTA1-7B | 43.4 | Not recorded | 6938fe876cfd488761a53c83 | | Qwen3VL-32B-Instruct | 43.1 | Not recorded | 6938fe876cfd488761a53c83 | | GUI-Actor-2.5VL-7B | 38.1 | Not recorded | 6938fe876cfd488761a53c83 | | UI-TARS-1.5-7B | 36.4 | Not recorded | 6938fe876cfd488761a53c83 | | UGround-V1-72B | 31.1 | Not recorded | 6938fe876cfd488761a53c83 | | UGround-V1-7B | 28.1 | Not recorded | 6938fe876cfd488761a53c83 | | Claude Computer Use | 12.6 | Not recorded | 6938fe876cfd488761a53c83 | | GPT-4o | 0.7 | Not recorded | 6938fe876cfd488761a53c83 | | SeeClick-7B | 0.3 | Not recorded | 6938fe876cfd488761a53c83 | ### Qwen3VL-32B-Instruct Development Score: 71.6. Result ID: 69986e745698665ec4ce5c80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"framework":"MVP"}. This record does not assert independent reproduction. ### UI-TARS-1.5 Development Score: 63.9. Result ID: 69986e745698665ec4ce5c68. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Closed-source"}. This record does not assert independent reproduction. ### Qwen3VL-8B-Instruct Development Score: 61.5. Result ID: 69986e745698665ec4ce5c7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"framework":"MVP"}. This record does not assert independent reproduction. ### UI-Venus-72B Development Score: 59.5. Result ID: 69986e745698665ec4ce5c72. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### GTA1-7B Development Score: 58.9. Result ID: 69986e745698665ec4ce5c7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"framework":"MVP"}. This record does not assert independent reproduction. ### GUI-Cursor-7B Development Score: 57.5. Result ID: 69986e745698665ec4ce5c76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### GTA1-72B Development Score: 57.2. Result ID: 69986e745698665ec4ce5c6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### UI-INS-32B Development Score: 55.8. Result ID: 69986e745698665ec4ce5c77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### Seed1.5-VL Development Score: 53.8. Result ID: 69986e745698665ec4ce5c69. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Closed-source"}. This record does not assert independent reproduction. ### GUI-Spotlight Development Score: 53.3. Result ID: 69986e745698665ec4ce5c75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### Qwen3VL-8B-Instruct Development Score: 52.8. Result ID: 69986e745698665ec4ce5c7d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"framework":"Baseline"}. This record does not assert independent reproduction. ### UI-TARS-1.5-7B Development Score: 51.8. Result ID: 69986e745698665ec4ce5c7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"framework":"MVP"}. This record does not assert independent reproduction. ### RegionFocus (Qwen2.5VL-72B) Development Score: 51.2. Result ID: 69986e745698665ec4ce5c6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### Qwen2.5-VL-32B-Instruct Development Score: 48.8. Result ID: 69986e745698665ec4ce5c6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### HyperClick Development Score: 46.9. Result ID: 69986e745698665ec4ce5c78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### V2P-7B Development Score: 46.8. Result ID: 69986e745698665ec4ce5c73. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### GMS (Gemini-2.5-Flash-Lite) Development Score: 44.8. Result ID: 69986e745698665ec4ce5c74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### SE-GUI-7B Development Score: 44.5. Result ID: 69986e745698665ec4ce5c71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### GTA1-7B Development Score: 43.4. Result ID: 69986e745698665ec4ce5c7b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"framework":"Baseline"}. This record does not assert independent reproduction. ### Qwen3VL-32B-Instruct Development Score: 43.1. Result ID: 69986e745698665ec4ce5c7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"framework":"Baseline"}. This record does not assert independent reproduction. ### GUI-Actor-2.5VL-7B Development Score: 38.1. Result ID: 69986e745698665ec4ce5c70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### UI-TARS-1.5-7B Development Score: 36.4. Result ID: 69986e745698665ec4ce5c79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"framework":"Baseline"}. This record does not assert independent reproduction. ### UGround-V1-72B Development Score: 31.1. Result ID: 69986e745698665ec4ce5c6c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### UGround-V1-7B Development Score: 28.1. Result ID: 69986e745698665ec4ce5c6b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. ### Claude Computer Use Development Score: 12.6. Result ID: 69986e745698665ec4ce5c67. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Closed-source"}. This record does not assert independent reproduction. ### GPT-4o Development Score: 0.7. Result ID: 69986e745698665ec4ce5c66. [Reporting paper]() Recorded evaluation configuration: {"Model Type":"Closed-source"}. This record does not assert independent reproduction. ### SeeClick-7B Development Score: 0.3. Result ID: 69986e745698665ec4ce5c6a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Type":"Open-source"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.