# Grounding on UI-Vision Source: [Grounding on UI-Vision]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:31:22.574Z Evaluation of Grounding performance on the UI-Vision dataset, measured using 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 | Grounding | | Dataset (including any stated split) | UI-Vision | | Metric | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | UI-Venus-1.5-30B-A3B | 54.7 | Not recorded | 698c0ceec97a0b3e3b5e104f | | MAI-UI-32B | 47.1 | Not recorded | 698c0ceec97a0b3e3b5e104f | | UI-Venus-1.5-8B | 46.5 | Not recorded | 698c0ceec97a0b3e3b5e104f | | UI-Venus-1.5-2B | 44.8 | Not recorded | 698c0ceec97a0b3e3b5e104f | | Holo2-30B-A3B | 40.9 | Not recorded | 698c0ceec97a0b3e3b5e104f | | MAI-UI-8B | 40.7 | Not recorded | 698c0ceec97a0b3e3b5e104f | | OpenCUA-72B | 37.3 | Not recorded | 698c0ceec97a0b3e3b5e104f | | UI-Venus-1.0-72B | 36.8 | Not recorded | 698c0ceec97a0b3e3b5e104f | | Holo2-8B | 35.1 | Not recorded | 698c0ceec97a0b3e3b5e104f | | OpenCUA-32B | 33.3 | Not recorded | 698c0ceec97a0b3e3b5e104f | | MAI-UI-2B | 30.3 | Not recorded | 698c0ceec97a0b3e3b5e104f | | Step-GUI-4B | 30 | Not recorded | 698c0ceec97a0b3e3b5e104f | | OpenCUA-7B | 29.7 | Not recorded | 698c0ceec97a0b3e3b5e104f | | UI-Venus-1.0-7B | 26.5 | Not recorded | 698c0ceec97a0b3e3b5e104f | | Qwen3-VL-30B-A3B | 25.6 | Not recorded | 698c0ceec97a0b3e3b5e104f | | UI-TARS-1.5-7B | 22.3 | Not recorded | 698c0ceec97a0b3e3b5e104f | | Qwen3-VL-8B | 21.9 | Not recorded | 698c0ceec97a0b3e3b5e104f | | Qwen3-VL-2B | 13.1 | Not recorded | 698c0ceec97a0b3e3b5e104f | ### UI-Venus-1.5-30B-A3B Accuracy: 54.7. Result ID: 699722185698665ec4705c24. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### MAI-UI-32B Accuracy: 47.1. Result ID: 699722185698665ec4705c21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### UI-Venus-1.5-8B Accuracy: 46.5. Result ID: 699722185698665ec4705c23. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### UI-Venus-1.5-2B Accuracy: 44.8. Result ID: 699722185698665ec4705c22. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### Holo2-30B-A3B Accuracy: 40.9. Result ID: 699722185698665ec4705c1d. [Reporting paper]() Recorded evaluation configuration: {"reproduction":true,"design":"end-to-end"}. This record does not assert independent reproduction. ### MAI-UI-8B Accuracy: 40.7. Result ID: 699722185698665ec4705c20. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### OpenCUA-72B Accuracy: 37.3. Result ID: 699722185698665ec4705c18. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### UI-Venus-1.0-72B Accuracy: 36.8. Result ID: 699722185698665ec4705c1b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### Holo2-8B Accuracy: 35.1. Result ID: 699722185698665ec4705c1c. [Reporting paper]() Recorded evaluation configuration: {"reproduction":true,"design":"end-to-end"}. This record does not assert independent reproduction. ### OpenCUA-32B Accuracy: 33.3. Result ID: 699722185698665ec4705c17. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### MAI-UI-2B Accuracy: 30.3. Result ID: 699722185698665ec4705c1f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### Step-GUI-4B Accuracy: 30. Result ID: 699722185698665ec4705c1e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"reproduction":true,"design":"end-to-end"}. This record does not assert independent reproduction. ### OpenCUA-7B Accuracy: 29.7. Result ID: 699722185698665ec4705c16. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### UI-Venus-1.0-7B Accuracy: 26.5. Result ID: 699722185698665ec4705c1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### Qwen3-VL-30B-A3B Accuracy: 25.6. Result ID: 699722185698665ec4705c15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"reproduction":true,"design":"end-to-end"}. This record does not assert independent reproduction. ### UI-TARS-1.5-7B Accuracy: 22.3. Result ID: 699722185698665ec4705c19. [Reporting paper]() Recorded evaluation configuration: {"design":"end-to-end"}. This record does not assert independent reproduction. ### Qwen3-VL-8B Accuracy: 21.9. Result ID: 699722185698665ec4705c14. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"reproduction":true,"design":"end-to-end"}. This record does not assert independent reproduction. ### Qwen3-VL-2B Accuracy: 13.1. Result ID: 699722185698665ec4705c13. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"reproduction":true,"design":"end-to-end"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.